INDEX

Explanations

and/or

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

others

-0.31

åīįåĲİ

-0.31

 others

-0.31

oma

-0.27

åħ¶å®ĥ

-0.27

 Others

-0.27

æģ¶

-0.26

 ander

-0.26

ä¸ĭéĿ¢å°ıç¼ĸ

-0.25

æľīä¸Ģå®ļ

-0.25

POSITIVE LOGITS

ence

0.26

dae

0.26

çĶļèĩ³

0.25

è¤ĩ

0.25

Ø²Ø§ÙĦ

0.25

 courtroom

0.24

å¤į

0.23

åĤ¬

0.23

abay

0.23

((*

0.23

Activations Density 0.016%

and/or

No Known Activations