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

 frequency

-0.27

é¢ĳçİĩ

-0.26

å»Ĭ

-0.25

Pan

-0.25

 prototype

-0.24

frequency

-0.24

pee

-0.24

 outputs

-0.24

 Vent

-0.24

Luz

-0.24

POSITIVE LOGITS

ystack

0.29

 Views

0.26

íĤ·

0.26

velle

0.25

Reality

0.25

çļĦæĥħå½¢

0.25

æ£«

0.25

 realistic

0.25

$$$$

0.25

utterstock

0.24

Activations Density 0.005%

No Known Activations

This feature has no known activations.