INDEX

Explanations

just

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

gÃ¼

-0.28

çŀĴ

-0.27

 Talks

-0.26

(arc

-0.24

ä¸įæŃ»

-0.24

arc

-0.24

åŁ

-0.24

(||

-0.24

mdi

-0.23

ermo

-0.23

POSITIVE LOGITS

éľĩæħĳ

0.25

å¹²è´§

0.25

ä½ľçĶ¨

0.24

zap

0.24

å±ķåĵģ

0.24

PasswordEncoder

0.23

æĽ´å¤ļçļĦæĺ¯

0.23

atel

0.23

é£İéĻ©

0.23

 Heritage

0.23

Activations Density 0.001%

just

No Comments

No Known Activations