INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itating

-0.27

.bs

-0.26

ridge

-0.26

ä¸»åħ¬

-0.25

åī§ä¸Ń

-0.25

tar

-0.25

.FONT

-0.24

æµ¦

-0.24

 kino

-0.24

éĴ¯

-0.24

POSITIVE LOGITS

Òĵ

0.29

ector

0.28

ph

0.26

sexual

0.26

Ð¢Ð¬

0.25

ÑģÑĥÐ´

0.24

 squirt

0.24

åıĭæĥħ

0.24

orable

0.24

brief

0.24

Activations Density 81.652%

No Known Activations

This feature has no known activations.