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

è±º

-0.29

åłĥ

-0.27

Ø£Ø´

-0.25

Cow

-0.25

åĬĩ

-0.24

æĥ³å¿µ

-0.24

ÑĤÐ¾Ðº

-0.24

æĹ©æĹ©

-0.24

ocity

-0.24

 Wolves

-0.24

POSITIVE LOGITS

èĦ±

0.29

iem

0.28

ç¾¤

0.26

æĸ½

0.25

åİŁæĿ¥æĺ¯

0.24

 Trad

0.24

	except

0.24

ç¬¬ä¸īä¸ª

0.24

èĵ¬

0.24

/inet

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.