INDEX

Explanations

speed, beginning

np_max-act · gemini-2.0-flash

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

(()

-0.28

Zag

-0.27

è®²åº§

-0.26

tin

-0.25

inski

-0.24

ensi

-0.24

 reflect

-0.23

 have

-0.23

Ã©

-0.23

ä¿¡æģ¯åıĳå¸ĥ

-0.23

POSITIVE LOGITS

æĹ¥çĽĬ

0.50

è¶ĬæĿ¥è¶Ĭ

0.49

éĢĲæ¸Ĳ

0.48

æ¸Ĳæ¸Ĳ

0.48

 becoming

0.47

 increasingly

0.47

è¶ĬæĿ¥è¶Ĭå¤ļ

0.46

ä¹Łè¶ĬæĿ¥è¶Ĭ

0.45

ä¹Łå¼Ģå§ĭ

0.43

åıĺå¾Ĺ

0.42

Activations Density 0.030%

speed, beginning

No Comments

No Known Activations