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

rens

-0.28

DebugEnabled

-0.27

$"

-0.25

 probing

-0.25

 glean

-0.24

@@@@

-0.23

ç¾İåŃ¦

-0.23

åĲĮåŁİ

-0.23

 carne

-0.23

$(

-0.23

POSITIVE LOGITS

RESSION

0.27

,</

0.25

åıī

0.25

ORK

0.24

&_

0.24

 cita

0.23

weet

0.23

ç½ĳè®¯

0.23

_environment

0.23

ixels

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.