© 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 · 11-RESID-POST-AA · 34857 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
34857

INDEX

Explanations

loop index

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

Ik

-0.08

 SetUp

-0.07

طائر

-0.07

[],

-0.07

ꡐ

-0.07

疚

-0.06

/not

-0.06

 nerv

-0.06

lim

-0.06

suf

-0.06

POSITIVE LOGITS

 chron

0.07

_rent

0.07

 Firewall

0.07

_channel

0.07

カップ

0.07

receipt

0.07

 Chronic

0.07

icia

0.07

ografia

0.07

_goto

0.07

Activations Density 0.007%

No Known Activations