neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻译准备中
基于配置的 CLI 工具,在命令输出到达 LLM 上下文之前进行压缩。
AI 翻译
Config-driven CLI tool that compresses command output before it reaches an LLM context
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
tokf.net — reduce LLM context consumption from CLI commands by 60–90%. Commands like git push, cargo test, and docker build produce verbose output packed with progress bars, compile noise, and boilerplate. tokf intercepts that output, applies a TOML filter, and emits only what matters — so your AI agent sees a clean signal instead of hundreds of wasted tokens. cargo test — 61 lines → 1 line: Without tokf With tokf git push — 8 lines → 1 line: Without tokf With tokf [README 설치·사용 부분 발췌] Installation查看完整 README ↗
目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
tokf.net — reduce LLM context consumption from CLI commands by 60–90%. Commands like git push, cargo test, and docker build produce verbose output packed with progress bars, compile noise, and boilerplate. tokf intercepts that output, applies a TOML filter, and emits only what matters — so your AI agent sees a clean signal instead of hundreds of wasted tokens. cargo test — 61 lines → 1 line: Without tokf With tokf git push — 8 lines → 1 line: Without tokf With tokf [README 설치·사용 부분 발췌] Installation查看完整 README ↗