INDEX

Explanations

technical/medical terms

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

å¼ĢåıĳåĪ©çĶ¨

-0.29

 olacaÄŁÄ±

-0.25

]|[

-0.25

veis

-0.24

 Clear

-0.24

_CLEAR

-0.23

uming

-0.23

 hereby

-0.23

ubits

-0.23

åħ³éĶ®æĺ¯

-0.23

POSITIVE LOGITS

zob

0.26

åĶĩ

0.26

xic

0.26

wa

0.24

å¤¸

0.24

opot

0.24

ä¹Łæľīä¸ĢäºĽ

0.24

isque

0.24

wij

0.24

Activations Density 0.005%

technical/medical terms

No Comments

No Known Activations