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

lessly

-0.26

icens

-0.26

.mozilla

-0.24

posit

-0.24

 ÙħÙĨÙĩØ§

-0.23

.ht

-0.23

cycl

-0.23

ØµØ§Ø±

-0.23

 gegenÃ¼ber

-0.22

itsu

-0.22

POSITIVE LOGITS

ivor

0.28

 partic

0.27

hog

0.26

 dirty

0.26

utivo

0.25

NOP

0.25

yan

0.25

å°İ

0.24

NOP

0.24

è´£ç¼ĸ

0.24

Activations Density 0.016%

No Known Activations

This feature has no known activations.