© 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 · 1416 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
1416

INDEX

Explanations

titles, suffixes, and names

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

Advertis

-0.08

spl

-0.07

 stre

-0.07

Putin

-0.07

sville

-0.07

imar

-0.07

çĶ±

-0.07

 yourselves

-0.07

åĵ

-0.07

ikon

-0.07

POSITIVE LOGITS

Jr

0.30

jr

0.19

aka

0.18

Sr

0.17

 alias

0.15

PhD

0.13

âĢİ

0.12

who

0.11

JR

0.11

aka

0.11

Activations Density 1.673%

No Known Activations