© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 15-RESID-POST-AA · 20834 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
20834

INDEX

Explanations

digits

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

 topping

-0.08

_solve

-0.07

䈀

-0.07

DOS

-0.07

 Treasurer

-0.07

Bí

-0.07

 monitor

-0.07

瞪

-0.06

.Job

-0.06

 autorelease

-0.06

POSITIVE LOGITS

 congr

0.07

bg

0.07

ront

0.07

Fld

0.07

只知道

0.07

.IntegerField

0.07

河北省

0.07

lc

0.07

也能

0.07

 sheet

0.07

Activations Density 0.001%

No Known Activations