INDEX

Explanations

programming code

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

Ð¹ÑĤ

-0.29

 missed

-0.28

 disc

-0.27

åŀĴ

-0.26

CHIP

-0.26

èľİ

-0.26

ë¦½

-0.26

leigh

-0.26

 MISS

-0.26

/~

-0.26

POSITIVE LOGITS

ordinates

0.32

 Donovan

0.29

XYZ

0.28

 elems

0.26

>[]

0.26

 automobiles

0.25

æŃ¦åĬŁ

0.25

 sedan

0.25

OfWork

0.24

ä¼Ļ

0.24

Activations Density 0.017%

programming code

No Comments

No Known Activations