INDEX

Explanations

meet

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã©n

-0.26

èĭ¥å¹²

-0.25

(Language

-0.25

 Truly

-0.24

æĪĳçļĦ

-0.24

ä¸ĢåĪĩ

-0.24

-parser

-0.24

ERO

-0.23

èµĭ

-0.23

isher

-0.23

POSITIVE LOGITS

 growing

0.34

 increased

0.34

 growth

0.32

 upcoming

0.30

 scheduled

0.28

 ongoing

0.28

 higher

0.27

 demand

0.27

 structured

0.26

ypse

0.26

Activations Density 0.003%

meet

No Comments

No Known Activations