INDEX

Explanations

Es

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

hit

-0.27

æĿĥå¨ģ

-0.26

å®ŀä½ĵ

-0.26

Ð¸ÑĤÐµÐ»ÑĮÐ½Ð¾

-0.26

Add

-0.25

 Following

-0.24

 Storm

-0.24

ContentView

-0.24

 Shock

-0.24

é£İæļ´

-0.23

POSITIVE LOGITS

çķļ

0.28

LAT

0.28

 plag

0.28

æĮŁ

0.26

 uncomment

0.25

 pomi

0.25

lat

0.25

å§¿åĬ¿

0.24

èĳ«

0.24

LAT

0.23

Activations Density 0.045%

Es

No Comments

No Known Activations