INDEX

Explanations

numbers

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

KR

-0.33

 tide

-0.28

ption

-0.28

.kr

-0.27

 Kore

-0.27

PTION

-0.27

 blanket

-0.27

ivent

-0.27

Ø¨ÙĪØª

-0.25

 jeep

-0.25

POSITIVE LOGITS

HEMA

0.29

WAYS

0.28

eous

0.26

ç®Ĺ

0.26

è¯´å®Į

0.25

çİº

0.25

roat

0.24

InvalidArgumentException

0.24

EndInit

0.24

 child

0.24

Activations Density 0.008%

numbers

No Comments

No Known Activations