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

åł¡

-0.28

allet

-0.27

å¹¶ä¸įä¼ļ

-0.26

burg

-0.25

 Blockchain

-0.25

 firm

-0.24

åĮºåĿĹéĵ¾

-0.24

 author

-0.24

ukes

-0.24

al

-0.23

POSITIVE LOGITS

drag

0.28

 draining

0.26

ahan

0.26

ling

0.26

anyl

0.25

 drag

0.25

xEB

0.25

avana

0.25

xAE

0.24

LING

0.24

Activations Density 0.013%

No Known Activations

This feature has no known activations.