INDEX

Explanations

Al

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¾Īç®Ģåįķ

-0.28

NZ

-0.28

 immediate

-0.27

ennen

-0.26

aspberry

-0.26

nel

-0.25

stem

-0.25

rost

-0.25

 soar

-0.25

RING

-0.24

POSITIVE LOGITS

eway

0.27

.decrypt

0.26

ä¹ĺ

0.26

ìĤŃ

0.26

cast

0.25

Print

0.25

Printing

0.25

-Length

0.24

 alphanumeric

0.24

å·¡è§Ĩ

0.24

Activations Density 0.021%

Al

No Comments

No Known Activations