© 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 · 15-RESID-POST-AA · 127173 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
127173

INDEX

Explanations

Welcome

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

Negative Logits

irc

-0.08

考上

-0.07

都没

-0.07

 canadian

-0.07

irc

-0.06

€

-0.06

麒

-0.06

不排除

-0.06

[sub

-0.06

_Send

-0.06

POSITIVE LOGITS

おそ

0.07

*↵↵

0.07

 ?>
↵

0.07

科学发展

0.07

Quality

0.06

نظ

0.06

ﲪ

0.06

 ultr

0.06

 slowdown

0.06

.DefaultCellStyle

0.06

Activations Density 0.006%

No Known Activations