INDEX

Explanations

time

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åįĥéĩĮ

-0.29

zek

-0.28

º«

-0.27

 mean

-0.26

olia

-0.25

mod

-0.24

 exagger

-0.24

èº«

-0.24

åĩ¡æľ¬ç½ĳ

-0.24

ä¸ļç»©

-0.24

POSITIVE LOGITS

subclass

0.28

éģĹå¿ĺ

0.26

à¹Ģà¸Ļ

0.26

æİ§

0.25

ç°¿

0.24

Subset

0.24

 CHIP

0.24

xor

0.24

 hailed

0.24

CHIP

0.24

Activations Density 0.001%

time

No Comments

No Known Activations