INDEX

Explanations

technical/descriptions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĩĳèī²

-0.28

ä¸įå®ļ

-0.26

colo

-0.25

alem

-0.25

èĲ§

-0.25

 cult

-0.25

aleb

-0.24

entric

-0.24

äº¤åıī

-0.24

/Branch

-0.24

POSITIVE LOGITS

Mask

0.28

ç½ĳå°ıç¼ĸ

0.27

 cavity

0.26

æ³ķå¾ĭè§Ħå®ļ

0.26

buffers

0.26

mask

0.25

illi

0.25

 masking

0.25

FY

0.25

xCA

0.25

Activations Density 0.033%

technical/descriptions

No Comments

No Known Activations