INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¥Ķ

-0.30

æĭľ

-0.29

Responder

-0.26

mere

-0.26

dere

-0.25

æıĲéĢŁ

-0.25

å¯¿åĳ½

-0.25

è¤Ĭ

-0.24

avings

-0.24

mes

-0.24

POSITIVE LOGITS

emento

0.31

åĽ½éĻħåĮĸ

0.30

ksam

0.27

åħīèį£

0.27

WithMany

0.26

WithName

0.26

 elements

0.26

å§Ķå®£ä¼ł

0.25

 Disneyland

0.25

-China

0.25

Activations Density 48.731%

No Known Activations

This feature has no known activations.