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

aciones

-0.31

 capitalists

-0.25

roys

-0.24

 userEmail

-0.24

bank

-0.24

anti

-0.23

 GÃ¤

-0.23

 Downtown

-0.23

 past

-0.23

anto

-0.22

POSITIVE LOGITS

idia

0.27

.Sequential

0.25

,{"

0.24

èĩªè±ª

0.24

cura

0.24

lify

0.23

ucas

0.23

dh

0.23

-par

0.23

æ¤¹

0.23

Activations Density 0.020%

No Known Activations

This feature has no known activations.