INDEX

Explanations

interrogation

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

åıĳèµ·

-0.30

è°ĥæŁ¥æĺ¾ç¤º

-0.28

åħ³èģĶäº¤æĺĵ

-0.28

æĬ¥åĳĬæĺ¾ç¤º

-0.28

 negative

-0.26

æ½®

-0.25

æ·»

-0.25

erior

-0.25

æ±²

-0.25

dings

-0.25

POSITIVE LOGITS

 Calendar

0.28

æ·¹æ²¡

0.28

ä¿®å£«

0.26

 muscle

0.26

arah

0.25

Calendar

0.25

åľĨæ»¡å®ĮæĪĲ

0.25

mus

0.25

çº¯æ´ģ

0.25

HAR

0.24

Activations Density 0.853%

interrogation

No Comments

No Known Activations