INDEX

Explanations

looking

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å°¾å·´

-0.31

å¥½äºĭ

-0.31

äººäºĭ

-0.27

 sauna

-0.26

ooks

-0.26

å¤´éĥ¨

-0.26

ilm

-0.26

åĮ¡

-0.25

äººå®¶

-0.25

confirmation

-0.25

POSITIVE LOGITS

 Above

0.30

Above

0.29

 above

0.28

above

0.28

ä¸Ĭè¿°

0.26

 Strings

0.26

çº§ä»¥ä¸Ĭ

0.26

elow

0.25

 afore

0.25

ç¨Ķ

0.25

Activations Density 0.002%

looking

No Comments

No Known Activations