© 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 · 117050 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
117050

INDEX

Explanations

online article links

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

Lun

-0.08

CIS

-0.07

üp

-0.07

İR

-0.07

Tri

-0.07

렵

-0.07

traî

-0.06

Bra

-0.06

 classe

-0.06

 Tunis

-0.06

POSITIVE LOGITS

こちら

0.07

 apologize

0.07

 stiffness

0.07

Excellent

0.07

attery

0.07

_src

0.07

(E

0.06

 emulate

0.06

 everyone

0.06

 forState

0.06

Activations Density 0.015%

No Known Activations