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

å¢¨

-0.35

cin

-0.28

\Collection

-0.27

åħħåĪĨ

-0.26

\Command

-0.25

asmine

-0.24

-death

-0.24

ainen

-0.24

cripts

-0.23

IEnumerator

-0.23

POSITIVE LOGITS

ç«º

0.29

çľĭä¸Ģçľĭ

0.28

æ·±åĬłå·¥

0.26

 Complex

0.25

Assertion

0.25

fv

0.25

volution

0.25

ctp

0.24

èĢĥçĤ¹

0.24

 aggress

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.