© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 123398 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
123398

INDEX

Explanations

counsel

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

堾

-0.08

 Split

-0.07

caa

-0.07

losed

-0.06

.The

-0.06

ercicio

-0.06

 szczegół

-0.06

 scoff

-0.06

ataires

-0.06

gia

-0.06

POSITIVE LOGITS

dating

0.08

_soup

0.08

 współpr

0.07

部主任

0.07

FRE

0.07

_eff

0.07

 paperwork

0.07

تصوير

0.07

_pd

0.07

DWC

0.07

Activations Density 0.000%

No Known Activations