INDEX

Explanations

(

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĪĩ

-0.31

å¼Ł

-0.26

æĺ¯æľĢ

-0.25

 edition

-0.24

åºľ

-0.24

 details

-0.23

cut

-0.23

æĺ¯æľĢå¥½çļĦ

-0.23

 shall

-0.23

 slice

-0.23

POSITIVE LOGITS

åĲįä¹ī

0.27

ASTE

0.26

.$$

0.26

ä¸įè¶³ä»¥

0.26

spacer

0.26

skins

0.25

 #####

0.25

vens

0.24

_remain

0.24

)".

0.24

Activations Density 0.099%

(

No Comments

No Known Activations