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

ä¹¾

-0.29

ripp

-0.26

Ã¼h

-0.24

-duration

-0.24

road

-0.24

æµ·æĬ¥

-0.24

 Strait

-0.24

.AutoSizeMode

-0.24

ayscale

-0.23

æŁ©

-0.23

POSITIVE LOGITS

lie

0.27

ngo

0.26

è£

0.25

 Twins

0.25

åĨħé©¬

0.25

 dicks

0.24

ViewItem

0.24

æŃ¦å£«

0.24

orna

0.23

Proxy

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.