© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 39372 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
39372

INDEX

Explanations

a

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

 judged

-0.07

tol

-0.07

_gradient

-0.07

 BUTTON

-0.07

_cert

-0.06

gia

-0.06

 wavelength

-0.06

Tea

-0.06

 שנת

-0.06

 admon

-0.06

POSITIVE LOGITS

werp

0.07

لق

0.07

 manually

0.07

ﻝ

0.07

ctor

0.07

 крыш

0.07

.Shared

0.07

arte

0.06

.TextBox

0.06

ceiver

0.06

Activations Density 0.056%

No Known Activations