© 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 · 19-RESID-POST-AA · 70258 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
70258

INDEX

Explanations

code

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

给出

-0.08

 Kann

-0.07

�

-0.07

 Tent

-0.07

 nonsense

-0.07

stead

-0.07

turned

-0.07

 give

-0.07

Misc

-0.06

stdbool

-0.06

POSITIVE LOGITS

 professions

0.08

cheduling

0.07

(best

0.07

effects

0.07

גרפי

0.07

 impacts

0.07

':''

0.07

 PROFILE

0.07

ipelines

0.07

 youre

0.07

Activations Density 0.039%

No Known Activations