INDEX

Explanations

Science

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

ä¸ĭæīĭ

-0.30

opleft

-0.29

 Integral

-0.28

ãģĿãģĨãģ§

-0.27

eling

-0.26

 integral

-0.26

ç®Ģ

-0.26

Integral

-0.25

integral

-0.24

å¯¿

-0.24

POSITIVE LOGITS

ippi

0.30

UD

0.27

uff

0.26

é»¯

0.26

EDA

0.26

_PW

0.26

sub

0.26

IFF

0.24

EDIA

0.24

 Euler

0.24

Activations Density 0.001%

Science

No Comments

No Known Activations