© 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 · 15-RESID-POST-AA · 43889 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
43889

INDEX

Explanations

in

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 tenure

-0.08

نب

-0.07

vul

-0.07

(VALUE

-0.07

.visitMethodInsn

-0.07

 Nuggets

-0.07

ност

-0.07

 değerl

-0.07

 ceramics

-0.07

 defaultManager

-0.07

POSITIVE LOGITS

片刻

0.07

legend

0.07

我现在

0.07

{},↵

0.07

 Likewise

0.07

/pr

0.07

 THEN

0.07

一方

0.07

 chậm

0.07

亦

0.06

Activations Density 0.002%

No Known Activations