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

 discrim

-0.26

æ¿¯

-0.26

åħ

-0.25

 squirt

-0.25

 queries

-0.25

 movement

-0.25

æ£ĺ

-0.25

åķĲ

-0.25

 gest

-0.24

èĳ³

-0.24

POSITIVE LOGITS

resher

0.28

Ð´ÐµÐ¹

0.27

omba

0.26

olon

0.25

(vc

0.24

HC

0.24

fad

0.24

ì°¨

0.24

å²Ĺ

0.24

otropic

0.23

Activations Density 13.997%

No Known Activations

This feature has no known activations.