© 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-3-1125-32B · 32-RES-BATCHTOPK-131K · 87599 ｜ Neuronpedia

Home
Olmo-3-1125-32B
32-RES-BATCHTOPK-131K
87599

INDEX

Explanations

describes a state

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32

Prompts (Dashboard)

16,384 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

 Wich

-0.11

ilion

-0.10

 Georges

-0.10

 MÃ¼

-0.10

ocy

-0.10

 Maria

-0.10

 guts

-0.10

 casually

-0.09

Lou

-0.09

/get

-0.09

POSITIVE LOGITS

vis

0.10

 Majority

0.09

aup

0.09

OG

0.09

ialect

0.08

Hard

0.08

 racks

0.08

 Patri

0.08

 Hard

0.08

iley

0.08

Activations Density 0.183%

No Known Activations