neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻譯準備中
一套視覺化可觀測框架,適用於多代理系統,具有人性化代理、可見狀態、房間間移動,以及模型/代幣遙測功能。
AI 翻譯
A visual observability framework for multi-agent systems, featuring humanized agents, visible states, room-to-room movement, and model/token telemetry.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
The demo app ( npm run dev ) playing its scripted demonstration. Every agent, line and token figure in the demo is simulated. Embedded in your app, the office draws only what your events say.
Your agents already talk to each other. Now you can watch them do it.
A multi-agent run is a conversation you cannot see. The planner delegates, the coder calls tools, the reviewer objects, two agents meet and settle on a decision, and all you get is a wall of JSON scrolling past. Something blocks, and you go hunting through logs to find out who was waiting on whom.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
The demo app ( npm run dev ) playing its scripted demonstration. Every agent, line and token figure in the demo is simulated. Embedded in your app, the office draws only what your events say.
Your agents already talk to each other. Now you can watch them do it.
A multi-agent run is a conversation you cannot see. The planner delegates, the coder calls tools, the reviewer objects, two agents meet and settle on a decision, and all you get is a wall of JSON scrolling past. Something blocks, and you go hunting through logs to find out who was waiting on whom.檢視完整 README ↗