INDEX

Explanations

varied documents

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

çŃł

-0.28

 Essex

-0.28

chw

-0.28

 formatting

-0.26

Led

-0.25

Detroit

-0.24

YL

-0.24

zza

-0.24

Äħd

-0.24

zac

-0.24

POSITIVE LOGITS

 Turkish

0.32

åľŁèĢ³åħ¶

0.30

lige

0.29

 kÃ¼

0.28

 freezer

0.27

 mans

0.27

reve

0.27

æķķ

0.26

ospital

0.26

äºĤ

0.26

Activations Density 0.011%

varied documents

No Comments

No Known Activations