A model that is itself an expert in mechanistic interpretability. It reads another model’s internals — and tells you, in plain words, what it learned and where it lives.
Ask it anything. In any tongue.
Hermeneus reads the model’s internals and answers in plain language — a full conversation in one language, switching only when a new thread begins. It always opens in English.
Point it at a model. Three moves to an answer you can sign.
Reads the internals
Pythia’s paired traces, decomposed into sparse, named features — layer by layer.
Finds what fires
It locks onto the feature, the layer, the magnitude — learned, not memorized.
Explains it back
Plain language — your language — with the receipt attached.
Request early access. Invites roll weekly.
Hermeneus is in research preview. We’re onboarding teams shipping fine-tuned models who need to prove what changed — not guess.
On the list. ⟧
We’ll reach out from research@delphilab.ai with a preview invite. Check your inbox.
No spam · we read every request · γνῶθι σεαυτόν