© 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 · 85662 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
85662

INDEX

Explanations

Domain

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

 Football

-0.08

ยาก

-0.07

 Mars

-0.07

(td

-0.07

牡丹

-0.07

.open

-0.07

food

-0.07

.moveToFirst

-0.06

 мягк

-0.06

 Analysis

-0.06

POSITIVE LOGITS

corlib

0.07

趔

0.07

湮

0.07

''

0.07

ijkstra

0.07

//"

0.07

悅

0.07

xhr

0.06

벳

0.06

 abruptly

0.06

Activations Density 0.000%

No Known Activations