INDEX

Explanations

without

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿Ĳ

-0.28

Keyword

-0.27

éŃĳ

-0.26

<article

-0.26

ä¹Łä¸įä¾ĭå¤ĸ

-0.25

èľĹ

-0.25

éĻįä½İäºĨ

-0.24

æ¬ł

-0.24

ç¨ł

-0.24

 vite

-0.24

POSITIVE LOGITS

éĥ¡

0.30

.emit

0.29

otton

0.28

ifold

0.27

æĺİçĻ½

0.26

æĹģ

0.26

bastian

0.26

IndexOf

0.26

æĢĢ

0.26

/crypto

0.25

Activations Density 31.962%

without

No Comments

No Known Activations