© 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 · 2390 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
2390

INDEX

Explanations

Dr followed by a name

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

ede

-0.09

ible

-0.09

iano

-0.09

endant

-0.09

iston

-0.08

ents

-0.08

cd

-0.08

 chalk

-0.08

resco

-0.08

ef

-0.08

POSITIVE LOGITS

infeld

0.10

uml

0.09

illing

0.09

ums

0.09

abble

0.08

orang

0.08

hti

0.08

ILLED

0.08

aat

0.08

tel

0.08

Activations Density 0.107%

No Known Activations