INDEX

Explanations

digits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

æķĪ

-0.31

 createState

-0.27

å¤§è±¡

-0.27

:type

-0.26

æĹ¶éĹ´åĴĮ

-0.25

á»§ng

-0.25

Ð¾Ð±ÑħÐ¾Ð´Ð¸Ð¼

-0.24

TagName

-0.24

ERM

-0.24

asury

-0.24

POSITIVE LOGITS

0.28

æĮĩå°ĸ

0.28

æİ¥ç®¡

0.28

0.27

åħ¨æĹ¥åĪ¶

0.27

alah

0.26

ç»ķ

0.25

Õ³

0.25

|^

0.25

ãĥªãĤ¢ãĥ«

0.25

Activations Density 0.012%

digits

No Known Activations