© 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 · 62531 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
62531

INDEX

Explanations

container

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

 fascism

-0.10

北京市

-0.07

 jazz

-0.07

Mozilla

-0.07

road

-0.07

 Thành

-0.07

 Kumar

-0.07

 generating

-0.07

 comedy

-0.07

doctor

-0.06

POSITIVE LOGITS

 они

0.07

_-

0.07

_help

0.07

.lock

0.06

杖

0.06

ﺈ

0.06

@\

0.06

🌰

0.06

DOCTYPE

0.06

.AppCompatActivity

0.06

Activations Density 0.002%

No Known Activations