INDEX

Explanations

-ogenesis

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

å¥Ĥ

-0.27

 httpResponse

-0.27

few

-0.26

portun

-0.25

strup

-0.25

TouchEvent

-0.25

HttpException

-0.25

 Kami

-0.24

itical

-0.24

DMIN

-0.23

POSITIVE LOGITS

flo

0.28

!";↵

0.26

èĬ±æł·

0.25

 phá»ķ

0.25

æĢ»éĩı

0.25

atives

0.24

!';↵

0.24

Popular

0.23

æ²īæ·Ģ

0.23

_.

0.23

Activations Density 0.052%

-ogenesis

No Comments

No Known Activations