INDEX

Explanations

Non-English text

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

 Boot

-0.26

åģľçķĻ

-0.26

 crit

-0.25

 offline

-0.25

æ¢¨

-0.25

currentIndex

-0.24

ocation

-0.24

hal

-0.23

 currentPosition

-0.23

_Location

-0.23

POSITIVE LOGITS

èĽ±

0.26

obar

0.26

 anonymously

0.25

 bars

0.25

ä¹Ĵä¹ĵ

0.25

uits

0.24

RIES

0.24

 verv

0.24

çķı

0.24

å¦©

0.24

Activations Density 0.002%

Non-English text

No Comments

No Known Activations