neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
A guided read of edgar, the agent harness you can read in an afternoon: which files to open, in which order, and what to look for.
Developer toolsPython · JustGitHub @vespassassinaOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
The agent harness you can read in an afternoon. Any model. No hidden calls. Take the tour: vespassassina.github.io/edgar
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
The agent harness you can read in an afternoon.
Any model. No hidden calls. Nothing is done until it's verified.
Take A Tour of the Harness → a guided read
of the code, stop by stop, with diagrams.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
The agent harness you can read in an afternoon.
Any model. No hidden calls. Nothing is done until it's verified.
Take A Tour of the Harness → a guided read
of the code, stop by stop, with diagrams.Read the full README ↗