neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
Choose a Claude Code transcript and see how many input tokens each CLAUDE.md, rule, skill, memory and tool result cost, counted from the API usage the transcript records, next to the usual characters
Developer toolsPython · HTMLGitHub @peterwkdev-creatorOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
How much each source (CLAUDE.md, rules, skills, memory, tool results) costs in the context of a Claude Code session, counted from the API usage in its transcript. Also a context budget for CI, and the git version of each file a session loaded.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
How much each source (your CLAUDE.md, rules, skills, memory, tool results)
costs in the context of a Claude Code session, counted from the API usage
recorded in its transcript, not estimated from characters. For Claude Code
users who want to know what fills their context.
Or try it in the browser:
choose one of your transcripts, or run the synthetic example. The library runs
in the page (Pyodide); your file is never uploaded.
Reads only the transcripts under ~/.claude/projects on your machine.
Nothing is sent anywhere. The numbers are tokens, not dollars.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
How much each source (your CLAUDE.md, rules, skills, memory, tool results)
costs in the context of a Claude Code session, counted from the API usage
recorded in its transcript, not estimated from characters. For Claude Code
users who want to know what fills their context.
Or try it in the browser:
choose one of your transcripts, or run the synthetic example. The library runs
in the page (Pyodide); your file is never uploaded.
Reads only the transcripts under ~/.claude/projects on your machine.
Nothing is sent anywhere. The numbers are tokens, not dollars.Read the full README ↗