INDEX

Explanations

a

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

iom

-0.29

icl

-0.29

wol

-0.28

å¼ĵ

-0.28

itur

-0.28

eli

-0.27

inc

-0.27

iology

-0.26

ories

-0.26

mie

-0.26

POSITIVE LOGITS

 taps

0.29

æİ¨å¹¿

0.26

 :=↵

0.25

tap

0.25

<Class

0.24

rian

0.24

 Builders

0.24

ewis

0.24

é¼»åŃĲ

0.23

GA

0.23

Activations Density 0.002%

a

No Known Activations