INDEX

Explanations

zo

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 coun

-0.28

è°±

-0.27

 Formula

-0.26

 Ð¿Ð¾Ð»Ð¾Ð¶

-0.26

 actually

-0.25

 Advantage

-0.25

å±¿

-0.25

Formula

-0.25

Converted

-0.25

çħľ

-0.24

POSITIVE LOGITS

meth

0.33

ergy

0.31

æ³¨

0.30

 Pompeo

0.30

ifold

0.29

ivable

0.28

éĵĳ

0.27

ilio

0.26

ilded

0.26

å®Įå¥½

0.25

Activations Density 0.242%

zo

No Comments

No Known Activations