© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 3096 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
3096

INDEX

Explanations

li

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

ȼ

-0.08

shaw

-0.08

 вла

-0.07

ᠠ

-0.07

turnstile

-0.07

ᙳ

-0.06

TextBoxColumn

-0.06

activated

-0.06

acoes

-0.06

(T

-0.06

POSITIVE LOGITS

반

0.07

sł

0.07

 blogger

0.07

帮扶

0.07

合适

0.07

 ROUT

0.07

 expans

0.07

 потер

0.07

 пот

0.07

 WIFI

0.07

Activations Density 0.004%

No Known Activations