INDEX

Explanations

systems

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

xon

-0.27

electronics

-0.27

æŁŀ

-0.26

ë§ī

-0.25

dek

-0.24

Vect

-0.24

 progressives

-0.24

acias

-0.24

ophilia

-0.24

 spam

-0.24

POSITIVE LOGITS

 PROFILE

0.30

atan

0.27

bjerg

0.25

ãģ¹

0.25

äºŃ

0.25

ado

0.25

ÑģÑĮ

0.25

ureau

0.24

bat

0.24

äºĭä¸ļ

0.24

Activations Density 0.013%

systems

No Comments

No Known Activations