INDEX

Explanations

Technical documentation/research

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

range

-0.35

åĮºåŁŁåĨħ

-0.34

èĮĥçķ´

-0.34

å±ŀäºİ

-0.33

ä¸Ģç±»

-0.33

-range

-0.32

 range

-0.32

 genre

-0.31

çīĩåĮº

-0.31

-region

-0.31

POSITIVE LOGITS

 cach

0.29

orns

0.27

éĺĻ

0.26

Eu

0.26

MS

0.25

 Lazy

0.25

æİ¥éĢģ

0.24

 odom

0.24

Lazy

0.23

LTS

0.23

Activations Density 0.001%

Technical documentation/research

No Comments

No Known Activations