INDEX

Explanations

dec

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

@mail

-0.29

è¦ģçŁ¥éģĵ

-0.28

[cnt

-0.28

fact

-0.27

ç¨įå¾®

-0.27

 fact

-0.27

 wParam

-0.26

çºµåĲĳ

-0.25

å½ĵæĹ¶çļĦ

-0.25

.launch

-0.24

POSITIVE LOGITS

IONS

0.28

roots

0.26

ions

0.26

åĦ¿

0.26

µ

0.26

inya

0.25

åħ¨éĿ¢

0.25

itable

0.24

zym

0.24

å·¥ç¨ĭé¡¹çĽ®

0.24

Activations Density 0.063%

dec

No Comments

No Known Activations