INDEX

Explanations

plate

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

å¹´ä»¥æĿ¥

-0.27

emed

-0.27

æ¯Ľæ³½

-0.26

ration

-0.24

ya

-0.23

Raz

-0.23

çļĩåĨł

-0.23

minate

-0.23

addChild

-0.23

 ../../../

-0.23

POSITIVE LOGITS

noun

0.28

arend

0.26

ugh

0.26

uckles

0.25

(rhs

0.25

æŃ¦åĬŁ

0.25

å®³

0.24

Ven

0.24

 fallout

0.23

LAS

0.23

Activations Density 46.378%

plate

No Comments

No Known Activations