INDEX

Explanations

vice

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

prÃ©

-0.28

áºŃp

-0.27

_overflow

-0.26

-0.25

 Condition

-0.24

 Conditioning

-0.24

aminer

-0.23

dge

-0.23

ien

-0.23

POSITIVE LOGITS

éĿĴ

0.30

oze

0.29

ç¨¿

0.25

èĩ³æŃ¤

0.24

åı£è¯Ń

0.24

apro

0.24

EqualTo

0.24

 Goth

0.24

å¼

0.24

è¿Ńä»£

0.23

Activations Density 0.064%

vice

No Comments

No Known Activations