INDEX

Explanations

digits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

è½¯

-0.30

ä»¥å¤ĸ

-0.29

 morph

-0.28

èĵī

-0.28

cdn

-0.27

 soft

-0.26

¾

-0.25

morph

-0.25

}{$

-0.25

ded

-0.25

POSITIVE LOGITS

å¥ĹæĪ¿

0.28

æĪĳä»¬çŁ¥éģĵ

0.27

ibrate

0.27

utters

0.24

æİĮæŁľ

0.24

 Managers

0.24

ä¼ģä¸ļæıĲä¾Ľ

0.23

pheric

0.23

:str

0.23

 Liber

0.23

Activations Density 0.019%

digits

No Known Activations