© 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 · 56438 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
56438

INDEX

Explanations

whether or not

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

å¤Ħ

-0.12

enta

-0.11

hab

-0.10

)(((

-0.10

qual

-0.10

 Politico

-0.10

perf

-0.10

arel

-0.10

apter

-0.10

 âĨ

-0.10

POSITIVE LOGITS

ity

0.08

iu

0.07

sd

0.06

is

0.06

 deck

0.06

amp

0.06

 retract

0.06

.UR

0.06

yre

0.06

jump

0.06

Activations Density 0.002%

No Known Activations