INDEX

Explanations

Ni

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

_case

-0.25

.TestCase

-0.24

ä¸ĩä¸ª

-0.24

ä¾µçĬ¯

-0.24

åįķé¡¹

-0.23

mond

-0.23

 elemental

-0.23

riÃ³

-0.23

åĪĨè¡Į

-0.23

 deflate

-0.23

POSITIVE LOGITS

plate

0.26

SAVE

0.25

Rem

0.25

ÑģÐ»Ð¾Ð²

0.25

åİ

0.24

ìĤ´

0.24

lesi

0.24

 closely

0.24

 Downs

0.23

currentState

0.23

Activations Density 0.015%

Ni

No Comments

No Known Activations