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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĪ¸

-0.31

wid

-0.29

tip

-0.28

Ha

-0.27

bows

-0.25

å¨¶

-0.25

çĵ¦

-0.25

dialog

-0.24

hap

-0.24

åıĭ

-0.24

POSITIVE LOGITS

å¹Į

0.28

_pdata

0.27

oogle

0.25

ksam

0.25

olib

0.25

æ£Ĳ

0.25

egis

0.24

 Proto

0.24

(beta

0.24

 erle

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.