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

ubre

-0.26

REPORT

-0.26

 Fare

-0.26

Koh

-0.24

 forth

-0.24

 Line

-0.24

æĻļ

-0.24

forth

-0.24

nofollow

-0.23

agli

-0.23

POSITIVE LOGITS

/OR

0.32

çĶµè§Ĩ

0.29

etti

0.28

.cx

0.27

åĩºåĬ¨

0.26

ilver

0.26

ç»´æĮģ

0.25

DRAM

0.25

(dm

0.25

ouser

0.25

Activations Density 0.010%

No Known Activations

This feature has no known activations.