© 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 · 1781 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
1781

INDEX

Explanations

how followed by question words

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

anela

-0.09

ibi

-0.09

amus

-0.09

unan

-0.08

orn

-0.08

prime

-0.08

 Takes

-0.08

elige

-0.08

ERS

-0.08

lur

-0.08

POSITIVE LOGITS

/if

0.17

 much

0.16

far

0.15

itzer

0.15

beit

0.15

much

0.14

 fares

0.13

dy

0.13

soever

0.13

ling

0.13

Activations Density 0.590%

No Known Activations