INDEX

Explanations

employment

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

singleton

-0.29

å©Ĩ

-0.26

quotes

-0.26

ogle

-0.25

 monday

-0.24

pto

-0.24

éĹ®éģĵ

-0.24

oya

-0.24

udd

-0.24

TTY

-0.24

POSITIVE LOGITS

itors

0.30

æ³Ħ

0.26

yes

0.26

yes

0.26

åĵĩ

0.25

ç»ıèĲ¥æ´»åĬ¨

0.24

Yes

0.24

enser

0.24

æ¬£èµı

0.24

Yes

0.24

Activations Density 0.001%

employment

No Comments

No Known Activations