INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 forms

-0.31

å½¢å¼ı

-0.29

 form

-0.27

 formas

-0.26

 prÃ©s

-0.25

é½Ĳåħ¨

-0.25

forms

-0.24

SOS

-0.24

 sessionFactory

-0.24

 forma

-0.24

POSITIVE LOGITS

ural

0.25

orting

0.25

åĨ·æ°´

0.25

andest

0.24

Ded

0.24

wap

0.24

ç²Ł

0.23

.Mod

0.23

avra

0.23

æ±°

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.