INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utches

-0.32

éĺµèĲ¥

-0.30

 Scalars

-0.28

 notebooks

-0.26

 Scalar

-0.26

 kindly

-0.25

æ¢¦å¢ĥ

-0.25

infinity

-0.25

è§ī

-0.25

æ¢µ

-0.25

POSITIVE LOGITS

zeug

0.26

.EXTRA

0.26

DOC

0.24

åİĭæĬĳ

0.24

assy

0.24

ãģ¿

0.24

thur

0.23

 bulld

0.23

 underlying

0.23

æ±¶

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.