INDEX

Explanations

hold

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éļĲ

-0.28

ç»¼åĲĪæ²»çĲĨ

-0.27

åŃ°

-0.26

xBA

-0.26

tright

-0.26

æİĴåºı

-0.26

çļĦèĦ¸

-0.25

ossal

-0.24

 Banking

-0.24

è¯Ń

-0.24

POSITIVE LOGITS

å¥Ĺ

0.29

ancers

0.28

.nasa

0.27

uels

0.27

æ´¹

0.27

æĹ¶éĹ´åĴĮ

0.26

æĪĲåĬŁçİĩ

0.25

 sÆ¡

0.25

 errors

0.25

errors

0.25

Activations Density 0.022%

hold

No Comments

No Known Activations