INDEX

Explanations

fatal

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

ä¹ĭä¹¡

-0.31

ãĥªãĤ¢

-0.28

ä¹ĭæĺŁ

-0.27

èĬ±

-0.26

åĪĨå¸ĥåľ¨

-0.26

 thai

-0.26

ervo

-0.24

æĸľ

-0.24

èĵĿåĽ¾

-0.24

ä¼ģä¸ļæıĲä¾Ľ

-0.24

POSITIVE LOGITS

.MM

0.28

è¯ĳ

0.27

Seg

0.27

":"","

0.25

anness

0.25

lul

0.25

DIG

0.25

IEL

0.24

Console

0.24

/lg

0.24

Activations Density 1.196%

fatal

No Comments

No Known Activations