INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idian

-0.31

eting

-0.29

æŀĦ

-0.28

ä¸Ģå¹´ä¸Ģåº¦

-0.27

ä¸įå®Į

-0.26

ç«Ń

-0.25

/ay

-0.24

åĩĿ

-0.24

ä¸įæĪĲ

-0.24

(ex

-0.24

POSITIVE LOGITS

oeff

0.28

ctrine

0.25

iov

0.24

fileName

0.24

AGES

0.24

åĭĩ

0.24

 Mime

0.24

 soak

0.23

'::

0.23

 profession

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.