© 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 · 76191 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
76191

INDEX

Explanations

yield

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

simulation

-0.07

aba

-0.07

 Figure

-0.07

 notices

-0.07

 Dependencies

-0.07

 convin

-0.07

AD

-0.07

Ос

-0.06

ince

-0.06

 recruited

-0.06

POSITIVE LOGITS

 BEST

0.08

小微

0.08

촋

0.08

','=','

0.07

昡

0.07

 wpływ

0.07

 MessageBoxButton

0.07

滫

0.07

供养

0.07

EUR

0.07

Activations Density 0.069%

No Known Activations