© 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 · 19-RESID-POST-AA · 2081 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
2081

INDEX

Explanations

arm

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

兼

-0.07

 Azerbai

-0.07

 entertain

-0.07

投資

-0.07

而又

-0.06

 stall

-0.06

হ

-0.06

乐视

-0.06

_frames

-0.06

.capitalize

-0.06

POSITIVE LOGITS

 IMPLEMENT

0.07

ضم

0.07

销售人员

0.07

![↵

0.07

Dirty

0.07

le

0.06

 formulate

0.06

QN

0.06

 dolphin

0.06

穿上

0.06

Activations Density 0.038%

No Known Activations