© 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 · 2725 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
2725

INDEX

Explanations

PRIMARY KEY

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

ì°

-0.08

Ñħ

-0.07

 Empire

-0.06

 hairst

-0.06

 hind

-0.06

 coordinates

-0.05

 Judy

-0.05

 contempl

-0.05

 carts

-0.05

 overse

-0.05

POSITIVE LOGITS

ilarity

0.11

nin

0.11

ãĥ¼

0.11

strand

0.11

utions

0.10

ucha

0.10

.names

0.10

&e

0.10

.comp

0.10

OX

0.10

Activations Density 0.354%

No Known Activations