[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fxD_qmrnBizSjl_D3uIc17OIoL0UJS-ueW-THRm8yUuk":3},{"tool":4,"categoryPool":35},{"id":5,"name":6,"slug":7,"description":8,"url":9,"githubUrl":9,"openSource":10,"categories":11,"createdAt":16,"repo":17,"articles":33,"related":34},"entity_01m5t25e87e8jsqe7zh9ynnj9s","Neuron Explorer","neuron-explorer","Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results","https:\u002F\u002Fgithub.com\u002Flyramakesmusic\u002Fneuron-explorer",false,[12],{"name":13,"slug":14,"count":15},"Evals","evals",0,1792949795,{"id":18,"fullName":19,"url":9,"stars":20,"forks":21,"openIssues":22,"language":23,"license":24,"topics":25,"pushedAt":30,"archived":10,"licenseSpdx":31,"licenseOsi":10,"licenseVerifiedAt":32},"entity_01m5t25k07e4ca0nk9qb2bszw3","lyramakesmusic\u002Fneuron-explorer",1938,237,7,"Python","MIT",[26,27,28,29],"interpretability","mechanistic-interpretability","qwen","steering","2026-11-02T00:54:14Z","NONE","2026-10-25T17:36:39.825Z",[],[],[36,70,93,126],{"id":37,"name":38,"slug":39,"description":40,"url":41,"githubUrl":41,"logoUrl":42,"openSource":43,"categories":44,"createdAt":46,"repo":47,"company":62,"articles":68,"related":69},"entity_01kzhe2n9gfagsad1ydt1e7gkn","AACR-Bench","aacr-bench","An Alibaba open-source multi-language benchmark for evaluating LLMs in repository-level automatic code review, featuring an AI-assisted and expert-verified dataset.","https:\u002F\u002Fgithub.com\u002Falibaba\u002Faacr-bench","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Falibaba-0f6c077a.png",true,[45],{"name":13,"slug":14,"count":15},1786217846,{"id":48,"fullName":49,"url":41,"stars":50,"forks":51,"openIssues":52,"language":23,"license":53,"topics":54,"pushedAt":60,"archived":10,"licenseSpdx":53,"licenseOsi":43,"licenseVerifiedAt":61},"entity_01kzhe2qyzfagsad286a44dm07","alibaba\u002Faacr-bench",255,33,9,"Apache-2.0",[55,56,57,58,59],"benchmark","code-review","multi-language","repository-level-context","software-engineering","2026-10-15T07:13:55Z","2026-08-09",{"id":63,"name":64,"slug":65,"url":66,"bio":67,"githubOrg":65},"entity_01kzmeveq2f22bbn6jcepyspwk","Alibaba","alibaba","https:\u002F\u002Fwww.alibabagroup.com","Alibaba Open Source",[],[],{"id":71,"name":72,"slug":73,"description":74,"url":75,"githubUrl":76,"logoUrl":77,"openSource":43,"categories":78,"createdAt":80,"repo":81,"articles":91,"related":92},"entity_01kzpjy8r7fvn8q0rcmcw8xg56","BenchLocal","benchlocal","Test LLMs on real tasks. Compare models side-by-side.","https:\u002F\u002Fbenchlocal.com\u002F","https:\u002F\u002Fgithub.com\u002Fstevibe\u002FBenchLocal","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Fstevibe-cd02357b.png",[79],{"name":13,"slug":14,"count":15},1786390717,{"id":82,"fullName":83,"url":76,"stars":84,"forks":85,"openIssues":86,"language":87,"license":24,"topics":88,"pushedAt":89,"archived":10,"licenseSpdx":24,"licenseOsi":43,"licenseVerifiedAt":90},"entity_01kzpjybr1e4fah37p1vzk0558","stevibe\u002FBenchLocal",432,51,20,"TypeScript",[],"2026-08-10T15:10:36Z","2026-08-10",[],[],{"id":94,"name":95,"slug":96,"description":97,"url":98,"logoUrl":99,"openSource":10,"categories":100,"createdAt":105,"company":106,"articles":110,"related":125},"entity_01kyb2mdndeshatkngff89rdmc","Braintrust","braintrust","Ship quality agents at scale. Braintrust is the AI observability platform for tracing production, running evals, and catching regressions before they reach users.","https:\u002F\u002Fwww.braintrust.dev\u002F","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ficon180-ef918139.png",[101,102],{"name":13,"slug":14,"count":15},{"name":103,"slug":104,"count":15},"Observability","observability",1784930776,{"id":107,"name":95,"slug":96,"url":108,"bio":97,"githubOrg":109},"entity_01kzmevhdaf22bbn7meq79a9a8","https:\u002F\u002Fbraintrust.dev\u002F","braintrustdata",[111],{"id":112,"name":113,"slug":114,"summary":115,"url":116,"kind":117,"platform":118,"author":119,"authorHandle":120,"publisher":121,"publishedAt":122,"about":123,"writtenBy":124},"entity_01kyb1ndrmf6esz3naek99dvk8","The context gold rush: Why everyone is building the same thing.","the-context-gold-rush-why-everyone-is-building-the-same-thing","You either die building product or live long enough to do context management.","https:\u002F\u002Fx.com\u002Fsamzliu\u002Fstatus\u002F2080210797465379147","blog","x","Sam Z Liu","samzliu","X","2026-07-23",[],[],[],{"id":127,"name":128,"slug":129,"description":130,"url":131,"logoUrl":132,"openSource":10,"categories":133,"createdAt":135,"company":136,"articles":143,"related":155},"entity_01kzyfk0nweh5b7faygzq2rgzz","DataBench","databench","DataBench scores frontier AI on the analytics work that matters — reasoning, reporting, and investigation on realistic, messy warehouse data.","https:\u002F\u002Fhex.tech\u002Fdatabench\u002F","https:\u002F\u002Fr2.minima.ltd\u002Forg_01jakhtww5fk6b0jmxj0qfp9rf\u002Ffavicon-32ee2db0.svg",[134],{"name":13,"slug":14,"count":15},1786655638,{"id":137,"name":138,"slug":139,"url":140,"bio":141,"githubOrg":142},"entity_01kzyfhc52eh5b7fac540s653f","Hex","hex","https:\u002F\u002Fhex.tech","Finally — anyone can get data insights grounded in the facts of their business. Hex has a flexible approach to context that earns trust without slowing you down.","hex-inc",[144],{"id":145,"name":146,"slug":147,"summary":148,"url":149,"kind":150,"platform":118,"author":138,"authorHandle":151,"publisher":121,"publishedAt":152,"about":153,"writtenBy":154},"entity_01kzye6311esg9ae93nr6enft3","Introducing DataBench","introducing-databench","DataBench v1: 100 realistic analytical tasks across Q&A and open-ended prompts, run in a synthetic Hex workspace — built because existing analytics benchmarks test \"overspecified pub trivia\" rather than the vague, directional questions people actually ask.","https:\u002F\u002Fx.com\u002F_hex_tech\u002Fstatus\u002F2087946398390206512","article","_hex_tech","2026-08-13",[],[],[]]