INDEX

Explanations

technical and specialized information

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

ACY

-0.25

legen

-0.25

EXIT

-0.25

ç«¯

-0.25

 passage

-0.25

æĿĳ

-0.24

fix

-0.24

>";↵

-0.24

ucz

-0.24

 excer

-0.23

POSITIVE LOGITS

 Balls

0.29

esar

0.26

VN

0.26

ç²¾åŃĲ

0.25

-indent

0.25

 Trials

0.24

 Verd

0.24

å¤ļä½Ļ

0.24

VG

0.24

èĮĤ

0.24

Activations Density 0.064%

technical and specialized information

No Comments

No Known Activations