INDEX

Explanations

Code and Symbols

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

 unique

-0.28

/ajax

-0.28

æµı

-0.26

.apps

-0.25

terior

-0.25

UA

-0.24

 criterion

-0.24

unique

-0.24

 uniqueness

-0.24

urpose

-0.24

POSITIVE LOGITS

[](

0.25

Forum

0.24

ä¸ĵåĳĺ

0.24

ToSelector

0.24

æľįå½¹

0.24

cock

0.24

ictory

0.23

 straw

0.23

 finder

0.23

è®¢åįķ

0.23

Activations Density 0.013%

Code and Symbols

No Comments

No Known Activations