© 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 · 7-RESID-POST-AA · 80853 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
80853

INDEX

Explanations

p

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 kapsam

-0.07

threshold

-0.07

系列

-0.07

坼

-0.06

 Cipher

-0.06

相互

-0.06

tip

-0.06

碾

-0.06

烤

-0.06

厚度

-0.06

POSITIVE LOGITS

ibly

0.07

-information

0.07

Works

0.07

_hello

0.07

 setSearch

0.07

.Note

0.07

なの

0.07

购房

0.06

Inc

0.06

 insulin

0.06

Activations Density 0.005%

No Known Activations