INDEX

Explanations

Names and locations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

PP

-0.29

esson

-0.29

mpp

-0.27

.gnu

-0.27

dom

-0.27

æ¬º

-0.26

pub

-0.25

æ¬¡è¦ģ

-0.25

 friction

-0.25

pp

-0.25

POSITIVE LOGITS

ä¸Ģæŀ¶

0.28

chine

0.27

ä¼ļåıĳçĶŁ

0.26

 Calvin

0.26

:,

0.25

ä¹Ĵä¹ĵ

0.25

æ£ļ

0.25

åİį

0.25

ldr

0.25

 outdoors

0.24

Activations Density 0.014%

Names and locations

No Comments

No Known Activations