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

(signal

-0.32

sig

-0.31

sig

-0.31

ipe

-0.31

ç§ĺä¹¦

-0.28

:hidden

-0.27

sig

-0.27

ä¿¡åı·

-0.27

åĢį

-0.26

.sig

-0.26

POSITIVE LOGITS

lov

0.24

],[-

0.24

ullo

0.24

outu

0.23

æĹı

0.23

ÑĨÐ¾Ð²

0.23

Ð¾Ð²Ð°ÑĢ

0.23

 scrolls

0.23

Ä°Z

0.23

uestion

0.23

Activations Density 0.005%

No Known Activations

This feature has no known activations.