© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 120396 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
120396

INDEX

Explanations

coholic

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

 תפקיד

-0.07

 wła

-0.07

	exit

-0.07

و

-0.07

TM

-0.06

 loan

-0.06

Certainly

-0.06

.work

-0.06

 יתר

-0.06

ווי

-0.06

POSITIVE LOGITS

首付

0.07

 prevalence

0.07

 stove

0.07

*>(

0.07

ulares

0.06

מורים

0.06

就想

0.06

groupBy

0.06

draulic

0.06

ⵕ

0.06

Activations Density 0.005%

No Known Activations