INDEX

Explanations

(\

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å°»

-0.28

åĨµ

-0.27

enie

-0.27

obo

-0.25

 monastery

-0.25

åĮĸè¿Ľç¨ĭ

-0.25

 addItem

-0.25

 Bool

-0.24

vertime

-0.24

 liá»ĩt

-0.24

POSITIVE LOGITS

è¡Ķ

0.29

lush

0.28

åĪĿ

0.27

åģļå¾Ĺ

0.26

 corpor

0.25

 cuer

0.25

æıĲ

0.24

æıĲèµ·

0.23

 digest

0.23

digest

0.23

Activations Density 0.041%

(\

No Comments

No Known Activations