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

way

-0.29

 owner

-0.27

 fidelity

-0.26

owner

-0.25

iment

-0.25

 through

-0.24

ways

-0.24

aced

-0.24

att

-0.24

 corresponding

-0.24

POSITIVE LOGITS

ä¹Łä¸įä¾ĭå¤ĸ

0.27

 reve

0.25

ä¹Łè¶ĬæĿ¥è¶Ĭ

0.24

 \↵↵

0.24

æĹ¥æĻļéĹ´

0.24

HAM

0.24

POW

0.24

æĺİæľĹ

0.24

 Completely

0.23

æĹ¥æĻļ

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.