INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¢ĥ

-0.28

lename

-0.27

 VÅ©

-0.26

è±¹

-0.26

èĿĩ

-0.26

UCT

-0.25

meg

-0.25

ä¸ĩåĲ¨

-0.25

TON

-0.24

åĬ¨çĶŁæĪĲ

-0.24

POSITIVE LOGITS

 BÃ¼ro

0.28

 Raised

0.28

 Bord

0.27

zew

0.27

-appointed

0.26

 real

0.26

bring

0.26

çľŁ

0.26

Raised

0.26

æĴŃ

0.25

Activations Density 0.004%

No Known Activations

This feature has no known activations.