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

ongan

-0.28

ä¸Ģæĸ¹éĿ¢æĺ¯

-0.26

 inconsist

-0.26

 dela

-0.26

å¥ĩèĳ©

-0.25

 incompet

-0.25

 delimited

-0.25

é¬¼

-0.24

ives

-0.24

ONGL

-0.24

POSITIVE LOGITS

abella

0.29

abr

0.28

headline

0.27

ast

0.27

Ø§Ø³ÙĦ

0.26

dp

0.26

ÑĦÑĢ

0.25

ä¸Ŀ

0.25

æľ¬æĬ¥

0.25

ab

0.24

Activations Density 0.087%

No Known Activations

This feature has no known activations.