INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 versa

-0.29

å¥łå®ļäºĨ

-0.28

versed

-0.25

/setup

-0.24

itty

-0.24

(vc

-0.24

Ã¡ny

-0.23

inery

-0.23

é£ı

-0.23

phans

-0.23

POSITIVE LOGITS

å®¦

0.24

bay

0.24

.setSelection

0.24

ä¿ĿæĬ¤

0.24

è¯ģæį®

0.23

çĮĿ

0.23

peon

0.23

æĬ¢

0.23

åĬŁåĬ³

0.23

[[[

0.22

Activations Density 0.002%

No Known Activations

This feature has no known activations.