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

å¹´åĲİ

-0.28

æĸ°çīĪ

-0.26

/root

-0.26

<![

-0.25

å¹´ãģ«

-0.25

GMT

-0.24

lox

-0.24

å¹´èµ·

-0.24

ystery

-0.24

_DS

-0.24

POSITIVE LOGITS

ToBounds

0.29

 recomm

0.27

olumn

0.26

 thÃ¡i

0.25

åĨľåī¯äº§åĵģ

0.25

 concluded

0.25

 thumbnails

0.24

Po

0.24

 comprise

0.24

olina

0.24

Activations Density 27.173%

No Comments

No Known Activations