© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 96200 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
96200

INDEX

Explanations

('

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

Negative Logits

夢

-0.07

 Cuando

-0.07

طالب

-0.07

 Nombre

-0.07

 tendon

-0.07

Nombre

-0.07

监护

-0.07

 Judy

-0.07

 personalize

-0.07

 Sussex

-0.06

POSITIVE LOGITS

Availability

0.08

项目建设

0.07

/entities

0.07

 Representation

0.07

调查

0.06

财务管理

0.06

�

0.06

setScale

0.06

 đảm

0.06

╉

0.06

Activations Density 0.002%

No Known Activations