© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

OLMO-3-1025-7B · 16-RES-MATRYOSHKA-65K · 55668 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
55668

INDEX

Explanations

categories like

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

decoderesearch/olmo-3-saes/olmo-3-1025-7b

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enberg

-0.10

naz

-0.10

kee

-0.10

 targ

-0.09

loo

-0.09

wizard

-0.09

 Inbox

-0.09

 Innoc

-0.09

DI

-0.09

enburg

-0.09

POSITIVE LOGITS

ober

0.08

 stripper

0.07

bek

0.07

 Wiley

0.07

ahn

0.07

alse

0.07

Gar

0.07

 Summit

0.07

 eget

0.07

lam

0.06

Activations Density 0.009%

No Known Activations