INDEX

Explanations

je

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

åİ¿

-0.27

ians

-0.26

edad

-0.26

åĽ¾

-0.26

ä¿Ŀ

-0.25

å¹³åĿĩ

-0.25

 School

-0.25

åķĦ

-0.25

 åĽ¾

-0.25

Algorithm

-0.25

POSITIVE LOGITS

å¾ģæ±ĤæĦıè§ģ

0.29

åħľ

0.29

èį¼

0.28

ä¸Ģä¸ĸ

0.26

rine

0.26

éľı

0.26

æ´ĭæ´ĭ

0.26

çĤ·

0.25

 setInterval

0.24

/rules

0.24

Activations Density 0.165%

je

No Comments

No Known Activations