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

{Name

-0.25

ä¸Ģå®ļ

-0.24

asure

-0.24

æĶ¿æĿĥ

-0.24

Swe

-0.24

bour

-0.23

ä¼ĺåĬ¿

-0.23

å¸ĪäºĭåĬ¡æīĢ

-0.23

åŃº

-0.23

 scram

-0.23

POSITIVE LOGITS

-bg

0.27

legs

0.26

 dimensional

0.25

css

0.25

icz

0.25

åıĳæī¬

0.25

 Nicol

0.25

å¥ķ

0.24

å¼Ī

0.24

å¹´äºº

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.