INDEX

Explanations

Note

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Exterior

-0.26

åĻĮ

-0.25

resher

-0.25

elts

-0.25

ä¸ĥå¹´

-0.24

åķĲ

-0.24

lint

-0.24

entence

-0.24

ecz

-0.23

çļĦä½ľåĵģ

-0.23

POSITIVE LOGITS

 however

0.30

however

0.28

 enim

0.27

However

0.26

amu

0.25

 wasn

0.25

www

0.25

Unfortunately

0.25

 though

0.24

ä¹Łå¾Ī

0.24

Activations Density 0.031%

Note

No Comments

No Known Activations