© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

OLMO-3-1025-7B · 16-RES-MATRYOSHKA-65K · 54091 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
54091

INDEX

Explanations

of the

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

alc

-0.11

 Paso

-0.09

fy

-0.09

VO

-0.09

 Rice

-0.09

inux

-0.09

lobals

-0.09

umb

-0.09

Øº

-0.09

stry

-0.08

POSITIVE LOGITS

 titular

0.11

 obviously

0.10

 Naturally

0.08

pon

0.08

 understandably

0.08

lÃ©

0.08

 Hans

0.07

 Olsen

0.07

mou

0.07

 foul

0.07

Activations Density 0.253%

No Known Activations