© 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 · 57167 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
57167

INDEX

Explanations

No Explanations Found

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

æĳ

-0.08

abl

-0.08

alus

-0.08

ursors

-0.08

ê±°

-0.08

 multipart

-0.08

entiful

-0.08

ev

-0.07

ev

-0.07

uber

-0.07

POSITIVE LOGITS

Sue

0.10

[,]

0.09

 Sham

0.09

 anom

0.09

nap

0.09

[][]

0.09

Bee

0.08

Pam

0.08

 Skull

0.08

 Carnegie

0.08

Activations Density 0.000%

No Known Activations