INDEX

Explanations

mathematical equations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

è¾Ł

-0.27

 modify

-0.27

 karÅŁÄ±s

-0.26

VIR

-0.26

 catholic

-0.25

 Outputs

-0.25

idot

-0.25

cape

-0.25

bart

-0.25

åıĺå¼Ĥ

-0.24

POSITIVE LOGITS

æĮ¤åİĭ

0.29

dsa

0.27

 sque

0.27

 squeez

0.26

åĤĢ

0.26

 proport

0.24

åıĶ

0.24

å°¤åħ¶æĺ¯åľ¨

0.23

",-

0.23

walking

0.23

Activations Density 0.100%

mathematical equations

No Comments

No Known Activations