INDEX

Explanations

on

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

Lot

-0.26

 vision

-0.26

eyes

-0.24

æĿ¥æī¾

-0.24

TabPage

-0.24

Modes

-0.24

æĿ¥è¿Ľè¡Į

-0.24

 Honor

-0.24

urry

-0.24

.setSelection

-0.24

POSITIVE LOGITS

sei

0.30

å¤§çĪ·

0.29

çĪĨåıĳ

0.29

åĨľå®¶

0.28

roken

0.27

raries

0.26

åĨ³ä¸į

0.25

æĮŁ

0.25

ther

0.24

gue

0.24

Activations Density 0.076%

on

No Comments

No Known Activations