INDEX

Explanations

up

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

åıĳæĮ¥

-0.27

 raise

-0.26

å®¹

-0.26

å®¹éĩı

-0.25

raise

-0.25

æ¯ıä½į

-0.24

ritis

-0.24

æİĮæı¡

-0.24

æĶ¾æĿ¾

-0.24

ral

-0.24

POSITIVE LOGITS

æİĪ

0.34

AGER

0.30

optic

0.29

enson

0.27

oins

0.26

 exotic

0.26

OptionsMenu

0.25

çĿ£åĬŀ

0.25

Cas

0.25

otland

0.25

Activations Density 0.019%

up

No Comments

No Known Activations