© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

QWEN2.5-7B-IT · 15-RESID-POST-AA · 83252 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
83252

INDEX

Explanations

Myers-Briggs personality types

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

如何去

-0.07

口径

-0.07

ская

-0.07

ụ

-0.06

 Coll

-0.06

erd

-0.06

🐣

-0.06

��

-0.06

 dafür

-0.06

 Buck

-0.06

POSITIVE LOGITS

 textField

0.07

BigInt

0.07

.setting

0.06

FFFF

0.06

浊

0.06

excel

0.06

办好

0.06

0.06

txt

0.06

(df

0.06

Activations Density 0.001%

No Known Activations