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

ãĤĦãĤĬ

-0.28

 merch

-0.27

osis

-0.26

 sigu

-0.26

åĲĪèµĦåħ¬åı¸

-0.25

 repost

-0.24

#-

-0.24

 offsets

-0.24

æĥº

-0.24

-online

-0.24

POSITIVE LOGITS

 outside

0.29

ä»¥å¤ĸ

0.28

esco

0.26

 imper

0.25

è½°

0.25

cie

0.25

 Concent

0.24

å¤ĸçķĮ

0.24

 Carrier

0.24

éĽĨä¸Ń

0.24

Activations Density 0.784%

No Known Activations

This feature has no known activations.