© 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 · 2964 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
2964

INDEX

Explanations

software licenses

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

ç¨

-0.09

toArray

-0.08

PCS

-0.07

elig

-0.07

Attendance

-0.07

ogh

-0.07

igo

-0.07

uge

-0.07

 leveled

-0.07

.conf

-0.07

POSITIVE LOGITS

/LICENSE

0.19

/gpl

0.13

/lgpl

0.12

/MIT

0.10

\d

0.10

0.10

—he

0.09

edd

0.09

tu

0.09

_ON

0.09

Activations Density 0.008%

No Known Activations