© 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 · 39724 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
39724

INDEX

Explanations

its

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

ORIZATION

-0.07

 caractère

-0.07

 Appearance

-0.07

屬

-0.07

诤

-0.07

-Co

-0.07

 Wool

-0.07

READING

-0.07

ZIP

-0.07

榑

-0.06

POSITIVE LOGITS

胱

0.07

udiant

0.07

"strconv

0.07

 делать

0.07

{/

0.07

:flutter

0.06

(iterator

0.06

 rentals

0.06

 profits

0.06

_series

0.06

Activations Density 0.000%

No Known Activations