INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éģįå¸ĥ

-0.31

 impressions

-0.27

çľŁçļĦ

-0.26

 Shower

-0.26

Pru

-0.25

éĩįè¦ģçļĦ

-0.24

æĭĵ

-0.24

åĲ¸æĶ¶

-0.24

Gaz

-0.24

bearing

-0.24

POSITIVE LOGITS

strap

0.30

ä½ĵåĪ¶æľºåĪ¶

0.29

slot

0.28

-io

0.26

asticsearch

0.26

æĤ±

0.26

åĪĽæĸ°èĥ½åĬĽ

0.26

abet

0.24

acus

0.24

æľįåĬ¡èĥ½åĬĽ

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.