INDEX

Explanations

regulations and restrictions

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

yat

-0.28

 Chá»ĭ

-0.27

onta

-0.26

KeyListener

-0.25

 interviewer

-0.25

åįķè½¦

-0.25

innie

-0.24

 interpreter

-0.24

è¿«ä½¿

-0.23

ieve

-0.23

POSITIVE LOGITS

ä¸ĢçĽ´åĪ°

0.35

 until

0.33

çĽ´åĪ°

0.32

çĽ´èĩ³

0.31

ä»»ä½ķå½¢å¼ı

0.31

 till

0.29

åºĶåľ¨

0.27

æĪªèĩ³

0.27

 gestures

0.26

until

0.26

Activations Density 0.001%

regulations and restrictions

No Comments

No Known Activations