INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

finity

-0.29

ACLE

-0.28

bling

-0.28

section

-0.26

explained

-0.25

ceÄŁi

-0.25

hob

-0.25

Ð½ÐµÐ¶

-0.24

oment

-0.24

acam

-0.24

POSITIVE LOGITS

 returnUrl

0.26

 addObject

0.25

aju

0.25

åĴª

0.24

imus

0.24

gc

0.23

avs

0.23

awy

0.23

rÃ¥

0.22

etus

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.