INDEX

Explanations

Code and web content

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 among

-0.73

among

-0.68

 amongst

-0.63

 Among

-0.50

Among

-0.47

åħ¶ä¸Ńä¹ĭä¸Ģ

-0.44

 ÑģÑĢÐµÐ´Ð¸

-0.43

åħ¶ä¸Ń

-0.41

çŃīçŃī

-0.41

 just

-0.40

POSITIVE LOGITS

éĻ¢

0.28

uten

0.24

scope

0.24

suf

0.24

arian

0.24

Äįe

0.24

-src

0.23

åħĪè¿Ľ

0.23

ichten

0.23

obl

0.23

Activations Density 0.005%

Code and web content

No Comments

No Known Activations