© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

OLMO-3-1025-7B · 16-RES-MATRYOSHKA-65K · 8288 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
8288

INDEX

Explanations

for my / me

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

Negative Logits

ummings

-0.09

erre

-0.09

allen

-0.09

erset

-0.09

-0.08

ottes

-0.08

 Basis

-0.08

è¨

-0.08

 trouble

-0.08

ande

-0.08

POSITIVE LOGITS

him

0.11

 them

0.10

uf

0.09

akers

0.08

us

0.08

 someone

0.08

him

0.08

 Guar

0.08

Them

0.07

them

0.07

Activations Density 0.233%

No Known Activations