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
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證正在載入完整 README。 以下為已儲存的摘錄。
Analyzes a public GitHub repository and produces a saved, shareable Report: a
deterministic 0–100 Health Score, the objective Metrics it was computed
from, the Analysis Scope that was actually examined, and an AI-written
summary of strengths, risks, and suggestions.
The Health Score is a pure function of the Metrics. The AI summary is written
from those Metrics and never changes the score — and if the summary step
fails, the Report is still saved and shown, as a Partial Report.
See CONTEXT.md for the domain vocabulary and docs/adr/
for the reasoning behind the architecture.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。
Analyzes a public GitHub repository and produces a saved, shareable Report: a
deterministic 0–100 Health Score, the objective Metrics it was computed
from, the Analysis Scope that was actually examined, and an AI-written
summary of strengths, risks, and suggestions.
The Health Score is a pure function of the Metrics. The AI summary is written
from those Metrics and never changes the score — and if the summary step
fails, the Report is still saved and shown, as a Partial Report.
See CONTEXT.md for the domain vocabulary and docs/adr/
for the reasoning behind the architecture.檢視完整 README ↗