INDEX

Explanations

proceedings

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

æĲ¬å®¶

-0.33

-0.28

-0.27

 Ð¼

-0.27

éŁ©åĽ½

-0.26

è·ĳåİ»

-0.26

åį·

-0.25

irth

-0.25

unks

-0.25

éĤ£æ®µ

-0.25

POSITIVE LOGITS

eton

0.30

sure

0.26

.setResult

0.25

UDIO

0.25

uates

0.25

ramento

0.24

 Ð§ÑĤ

0.24

etermination

0.24

alar

0.24

erts

0.24

Activations Density 0.031%

proceedings

No Comments

No Known Activations