© 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 · 54538 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
54538

INDEX

Explanations

Legal case citations

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

odus

-0.10

etu

-0.08

 Ashton

-0.08

 Bret

-0.08

 prÃ³

-0.08

Spl

-0.08

igan

-0.07

actor

-0.07

CU

-0.07

ammer

-0.07

POSITIVE LOGITS

vex

0.11

 Randolph

0.09

vit

0.08

iling

0.08

neg

0.08

 Paran

0.08

att

0.08

vol

0.08

 Madd

0.08

 Inline

0.08

Activations Density 0.001%

No Known Activations