INDEX

Explanations

on

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

æ¼Ķå¥ı

-0.28

esModule

-0.27

instead

-0.26

éĩįä»»

-0.26

æ¼ĶåĶ±

-0.26

æ¼Ķåĩº

-0.25

è°±

-0.25

langs

-0.25

 alle

-0.24

ypsum

-0.24

POSITIVE LOGITS

éĥ¨åī¯

0.29

æĪªèĩ³

0.26

 Pilot

0.25

 boyfriend

0.25

åĩºå¢ĥ

0.25

éĥ¨

0.25

 Offensive

0.24

![

0.24

 Professor

0.23

 OFFSET

0.23

Activations Density 0.007%

on

No Comments

No Known Activations