INDEX

Explanations

Numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EC

-0.28

 endurance

-0.27

agh

-0.26

 inve

-0.26

ä¸ĢéĿ¢

-0.25

pha

-0.25

reu

-0.25

 scor

-0.25

ï¿½ï¿½

-0.25

emark

-0.24

POSITIVE LOGITS

å¯¹æĪĳä»¬

0.30

 shorts

0.28

å¯¹ä½ł

0.27

 tráº§n

0.27

TYPES

0.26

ç½Ĥ

0.26

 Libya

0.26

åĽłä¸ºä»ĸ

0.26

å¯¹å¥¹

0.26

 ÑģÐµÐ±Ðµ

0.25

Activations Density 0.015%

Numbers

No Comments

No Known Activations