INDEX

Explanations

GNU

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

ç»ıéªĮåĴĮ

-0.29

markt

-0.27

omain

-0.27

 tang

-0.27

wr

-0.26

ways

-0.26

æīįåıĳçİ°

-0.26

é¢Ľ

-0.26

isma

-0.26

sla

-0.25

POSITIVE LOGITS

è´

0.32

.gf

0.27

ANCH

0.26

ÙģØ³

0.25

'..

0.25

TagName

0.24

CHED

0.24

others

0.23

ç³Ĺ

0.23

 waving

0.23

Activations Density 0.037%

GNU

No Comments

No Known Activations