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

rez

-0.27

 mirrored

-0.27

razil

-0.26

èĩĤ

-0.26

éĻį

-0.26

å¸ĪèĮĥ

-0.25

Ã¡z

-0.24

è°ģçŁ¥éģĵ

-0.24

 past

-0.24

.SizeType

-0.23

POSITIVE LOGITS

æĸ¯é¡¿

0.31

ulant

0.29

selectAll

0.28

RAP

0.27

 userList

0.25

itti

0.24

ARD

0.24

 Canc

0.24

-simple

0.24

 Barnett

0.24

Activations Density 0.015%

No Known Activations

This feature has no known activations.