INDEX

Explanations

Jessica or favorite

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

åŃº

-0.29

ings

-0.28

è¯Ĭ

-0.28

Ã§Ä±

-0.28

lice

-0.27

con

-0.27

ä¸ĵå®¶

-0.26

""

-0.24

Traditional

-0.24

POSITIVE LOGITS

 lÃ£

0.27

 campground

0.27

_WAKE

0.26

hg

0.24

OMEM

0.24

elda

0.23

emailer

0.23

 Sundays

0.23

ilet

0.23

ckeditor

0.23

Activations Density 49.723%

Jessica or favorite

No Comments

No Known Activations