INDEX

Explanations

code, internet, academia

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

ose

-0.32

uale

-0.31

eden

-0.29

OSE

-0.29

 proposed

-0.28

ä¸Ģåī¯

-0.27

 proposing

-0.26

ogui

-0.26

Ð¾Ð·Ð´

-0.26

èĨ³

-0.26

POSITIVE LOGITS

ä»¥èī²

0.28

UNC

0.26

Ð»Ð¸Ð·

0.25

Cycle

0.25

cycle

0.25

der

0.24

UNCH

0.24

æĺİæľĹ

0.24

åŁİå¢Ļ

0.23

warts

0.23

Activations Density 0.000%

code, internet, academia

No Comments

No Known Activations