INDEX

Explanations

Dates

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

field

-0.28

ice

-0.27

aan

-0.27

zent

-0.26

SAN

-0.26

sect

-0.26

mond

-0.25

efa

-0.25

åĮºåŁŁ

-0.25

faf

-0.24

POSITIVE LOGITS

å¤§çº²

0.29

-syntax

0.29

æŀ¯çĩ¥

0.28

å¹¿æ³ĽåºĶçĶ¨

0.28

æŁ½

0.27

 Syntax

0.27

è¹Ī

0.26

 syntax

0.25

è¯´ä¸įå®ļ

0.25

èĴº

0.25

Activations Density 0.021%

Dates

No Comments

No Known Activations