INDEX

Explanations

Internet excerpts/articles

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

flag

-0.28

æľº

-0.28

 flag

-0.28

ä¹°åĪ°

-0.27

anel

-0.27

-flag

-0.26

Flag

-0.26

mys

-0.26

 proposition

-0.26

å½Ĵ

-0.25

POSITIVE LOGITS

éĹ¼

0.28

éĦ¯

0.25

åĬŁ

0.25

odega

0.25

isan

0.24

erus

0.24

.Designer

0.23

undy

0.23

å®½

0.23

ä¸Ģå±Ĥ

0.23

Activations Density 0.002%

Internet excerpts/articles

No Comments

No Known Activations