INDEX

Explanations

this/these

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

Negative Logits

-cart

-0.30

 SAME

-0.28

ä¾¿æĺ¯

-0.27

å°±æĺ¯

-0.26

åĲĮä¸Ģ

-0.25

å°±æĺ¯åľ¨

-0.25

ä¹ŁæŃ£æĺ¯

-0.25

-colored

-0.24

ê¸Ī

-0.24

ooter

-0.24

POSITIVE LOGITS

 likely

0.27

imonial

0.26

unlikely

0.26

æ¯ĭ

0.26

lef

0.25

uco

0.25

elt

0.25

 statement

0.25

è¿ĺä¸įéĶĻ

0.24

 study

0.24

Activations Density 0.004%

this/these

No Known Activations