© 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 · 16365 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
16365

INDEX

Explanations

plant

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

 peninsula

-0.08

 kontrol

-0.08

 jade

-0.08

 Regression

-0.08

 internacional

-0.08

 máu

-0.08

esc

-0.07

ToWorld

-0.07

 regression

-0.07

 approaching

-0.07

POSITIVE LOGITS

монт

0.08

….

0.07

 Ново

0.07

 plant

0.07

廠

0.07

 plants

0.07

小さい

0.07

しさ

0.07

感

0.07

çı

0.07

Activations Density 0.017%

No Known Activations