INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 seat

-0.28

seat

-0.28

Seat

-0.27

aos

-0.27

ä¿Ŀå¯Ĩ

-0.27

-seat

-0.26

 confidentiality

-0.25

åħ±åĪĽ

-0.25

ç¨İ

-0.25

 Seat

-0.25

POSITIVE LOGITS

 pedest

0.29

coded

0.29

volent

0.28

çľŁçļĦ

0.25

Injected

0.24

jure

0.24

è´Ŀå£³

0.24

 Ð´Ð°Ð½Ð½ÑĭÐ¼

0.24

 Holds

0.24

 powered

0.23

Activations Density 1.394%

code

No Comments

No Known Activations