INDEX

Explanations

mandatory/voluntary

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.appspot

-0.28

acon

-0.27

ebra

-0.27

 quick

-0.27

acious

-0.26

as

-0.26

icap

-0.25

é¡ºåĪ©

-0.25

 quicker

-0.24

quick

-0.24

POSITIVE LOGITS

èĢĮéĿŀ

0.33

èĢĮä¸įæĺ¯

0.32

 componente

0.28

ä¸ĢçĤ¹

0.27

nod

0.25

 rather

0.25

 service

0.24

 component

0.24

rather

0.24

Ð½Ð¾

0.24

Activations Density 0.004%

mandatory/voluntary

No Comments

No Known Activations