INDEX

Explanations

invisible

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

dad

-0.30

urg

-0.26

Ð»Ð¾ÑĤ

-0.26

_dataframe

-0.24

æ²³éģĵ

-0.24

ubern

-0.24

DIC

-0.24

æ¶ĪåĮĸ

-0.23

à¸«à¸§à¸¢

-0.23

udy

-0.23

POSITIVE LOGITS

 textured

0.26

 BaseEntity

0.25

\'

0.25

çĻ¾äº¿

0.25

åĬ²

0.25

 tape

0.24

 rall

0.24

åľ°ä¸Ĭ

0.24

ä»²

0.23

.TXT

0.23

Activations Density 0.369%

invisible

No Known Activations