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

 Redistribution

-0.29

ena

-0.28

 genu

-0.28

æ¹Ľ

-0.26

Self

-0.26

ene

-0.25

åįĹå±±

-0.25

èĢĥçĤ¹

-0.25

nome

-0.25

eny

-0.24

POSITIVE LOGITS

 Continent

0.28

åĳĹ

0.28

hÃ¤user

0.27

illow

0.27

 catalogs

0.25

/&

0.25

<decltype

0.25

houses

0.25

hook

0.25

AGES

0.25

Activations Density 0.017%

No Known Activations

This feature has no known activations.