© 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 · 40029 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
40029

INDEX

Explanations

years

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

Counter

-0.07

 someone

-0.07

.co

-0.07

Dec

-0.07

 COVID

-0.07

umed

-0.07

 isEmpty

-0.06

Timing

-0.06

.getTime

-0.06

":"'

-0.06

POSITIVE LOGITS

_THAN

0.07

 subdir

0.07

变为

0.07

 sprzęt

0.07

剟

0.07

.serial

0.07

redd

0.06

ания

0.06

צרי

0.06

ǳ

0.06

Activations Density 0.036%

No Known Activations