© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

OLMO-3-1025-7B · 16-RES-MATRYOSHKA-65K · 953 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
953

INDEX

Explanations

separators followed by words

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

-0.07

à¤Ĥ

-0.07

-wise

-0.07

lington

-0.06

-0.06

 Remaining

-0.06

[,]

-0.06

nes

-0.06

Remaining

-0.06

LA

-0.06

POSITIVE LOGITS

aka

0.12

formerly

0.11

&_

0.10

::.

0.10

noch

0.10

 part

0.10

kart

0.10

shiv

0.10

azor

0.10

 narc

0.10

Activations Density 2.280%

No Known Activations