INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¯±

-0.28

 giorn

-0.27

 Platt

-0.26

ä»ĸåıĪ

-0.25

ä¸Ģå¤©

-0.25

ambah

-0.24

 eased

-0.24

Éµ

-0.24

ertiary

-0.24

 brokerage

-0.24

POSITIVE LOGITS

ç¢§

0.28

éĥ½åºĶè¯¥

0.27

TextLabel

0.27

.Dropout

0.26

sit

0.26

(("

0.25

 GetUser

0.25

brit

0.25

å§ĵ

0.24

phans

0.24

Activations Density 34.066%

No Known Activations

This feature has no known activations.