INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¹½

-0.31

 arms

-0.30

èħ¹

-0.28

vo

-0.27

åĲ¸

-0.26

Transmission

-0.26

Vo

-0.26

å¼§

-0.25

 best

-0.25

istr

-0.24

POSITIVE LOGITS

gle

0.30

osite

0.29

umed

0.27

allah

0.26

gles

0.26

ogle

0.26

OAD

0.25

IOD

0.25

_activate

0.24

 NDEBUG

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.