INDEX

Explanations

at

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

exas

-0.27

>>&

-0.25

 appended

-0.25

ÙĪÙĨÙĬ

-0.25

SEO

-0.25

çĵ®

-0.25

atics

-0.24

URA

-0.24

çĶ©

-0.24

åĽĽæĸ¹

-0.24

POSITIVE LOGITS

çŁ¥åĲįåº¦

0.31

achu

0.30

è£ģåĪ¤

0.29

 delicate

0.28

ju

0.25

Jud

0.25

.invoke

0.24

umu

0.24

å®¡åĪ¤

0.24

erving

0.24

Activations Density 0.016%

at

No Comments

No Known Activations