INDEX

Explanations

elsen

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lyph

-0.27

sei

-0.27

æĢİä¹ĪåĬŀ

-0.25

Bins

-0.25

pees

-0.24

è¿ĻåĿĹ

-0.24

Ã©ny

-0.24

åİ¿åŁİ

-0.24

 PLATFORM

-0.23

çĶŁçĶŁ

-0.23

POSITIVE LOGITS

ered

0.24

Vul

0.24

 displaced

0.24

åĦ¿

0.24

Gl

0.23

SCO

0.23

åł¡

0.23

 Gram

0.23

"**

0.22

 jButton

0.22

Activations Density 37.704%

elsen

No Comments

No Known Activations