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
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opinionated meta-cli that wraps codex/claude and encourages running 100s of agents at once
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Rudder runs coding agents the way they should be used: several at once,
isolated, reviewable, and easy to merge. It opens a native three-pane dashboard,
gives isolated tasks their own jj workspace, and runs real Claude Code or Codex
processes in the worker pane. Plain requests instead get one end-to-end owner in
the main checkout, so implementation, release, and deployment do not fall between
separate agents unless you explicitly ask for a DAG.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。
Rudder runs coding agents the way they should be used: several at once,
isolated, reviewable, and easy to merge. It opens a native three-pane dashboard,
gives isolated tasks their own jj workspace, and runs real Claude Code or Codex
processes in the worker pane. Plain requests instead get one end-to-end owner in
the main checkout, so implementation, release, and deployment do not fall between
separate agents unless you explicitly ask for a DAG.檢視完整 README ↗