INDEX

Explanations

time adverbs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IGN

-0.29

 Pháº¡m

-0.26

 Cookbook

-0.26

onta

-0.25

uet

-0.25

 Shutterstock

-0.25

äºĶæľĪ

-0.25

Feel

-0.25

äºĭä¸ļåıĳå±ķ

-0.25

 Juliet

-0.24

POSITIVE LOGITS

 cabe

0.28

 cane

0.27

 cort

0.27

çļĦåħ³éĶ®

0.26

iris

0.26

å¼Ģåĩº

0.25

æĪĳå¦Ī

0.24

rightness

0.24

 Constructor

0.24

å¯¹æĸ¹

0.24

Activations Density 0.003%

time adverbs

No Comments

No Known Activations