INDEX

Explanations

formal writing

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

uppe

-0.33

 defaults

-0.28

ival

-0.26

è¿Ļä¸ªæ¸¸æĪı

-0.25

 **/↵

-0.25

æ¾³

-0.25

éĹ´éļĻ

-0.25

ä¸įè¶³ä»¥

-0.25

åĢ¼å¾Ĺä¸Ģ

-0.25

 Pipe

-0.24

POSITIVE LOGITS

åĪ·

0.28

CHAN

0.27

Century

0.26

truth

0.26

icester

0.25

comic

0.25

comed

0.25

åĭ¤å¥ĭ

0.25

&(

0.25

terior

0.24

Activations Density 0.004%

formal writing

No Comments

No Known Activations