INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arters

-0.28

iefs

-0.27

iasi

-0.27

 signatures

-0.27

 modifiers

-0.26

acionales

-0.25

 Squad

-0.25

ANCH

-0.25

appers

-0.24

éº

-0.24

POSITIVE LOGITS

tery

0.25

 objective

0.25

 Objective

0.24

åı¨

0.24

alez

0.24

(compact

0.24

 Norwich

0.24

addtogroup

0.24

 relative

0.23

ä½Ĩä¸įéĻĲ

0.23

Activations Density 0.017%

No Known Activations

This feature has no known activations.