© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 24338 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
24338

INDEX

Explanations

and

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

是非

-0.08

achelor

-0.08

 Benchmark

-0.08

 Markdown

-0.07

 seekers

-0.07

,"

-0.07

Iran

-0.07

.For

-0.07

cho

-0.07

 Firstly

-0.07

POSITIVE LOGITS

أفل

0.07

軟

0.07

ⓕ

0.07

苦苦

0.07

 alternating

0.06

-ending

0.06

挣扎

0.06

回味

0.06

 entr

0.06

按键

0.06

Activations Density 0.026%

No Known Activations