INDEX

Explanations

ago

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

 complete

-0.28

ar

-0.27

Nug

-0.25

 publicity

-0.25

éĴ»

-0.24

nd

-0.23

 broadcast

-0.23

avel

-0.23

 guarantee

-0.23

complete

-0.23

POSITIVE LOGITS

ç²Ĺ

0.27

srv

0.27

 kort

0.27

 lined

0.27

circ

0.26

.mit

0.26

rts

0.26

ç²Ĺç³Ļ

0.25

à¹Ħà¸¥

0.25

/terms

0.24

Activations Density 0.003%

ago

No Comments

No Known Activations