© 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

QWEN2.5-7B-IT · 19-RESID-POST-AA · 7608 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
7608

INDEX

Explanations

cryptography and factoring

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

드

-0.08

Ped

-0.07

.jquery

-0.07

 organise

-0.07

 הקר

-0.07

por

-0.07

 }}>↵

-0.07

.icon

-0.06

猢

-0.06

WORDS

-0.06

POSITIVE LOGITS

סע

0.08

-outs

0.07

ほど

0.07

🗝

0.07

 dismay

0.07

 setbacks

0.07

_DECREF

0.07

뭣

0.07

 upsetting

0.07

✭

0.06

Activations Density 0.006%

No Known Activations