© 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 · 17012 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
17012

INDEX

Explanations

latter

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

Forgery

-0.08

禤

-0.07

⒡

-0.07

ableView

-0.07

влекатель

-0.07

anything

-0.07

.RequestParam

-0.07

opic

-0.07

inosaur

-0.07

constexpr

-0.07

POSITIVE LOGITS

 latter

0.10

0.07

 เป

0.07

Wa

0.07

ừa

0.07

 agency

0.07

 BUFFER

0.07

从而

0.06

 lobby

0.06

מיד

0.06

Activations Density 0.004%

No Known Activations