INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĭĬ

-0.30

olen

-0.30

alen

-0.29

obel

-0.29

å¤ķ

-0.28

enze

-0.28

ä¸Ģæ³¢

-0.26

ondere

-0.26

.Gradient

-0.25

Grace

-0.25

POSITIVE LOGITS

0.32

0.31

Ton

0.30

imm

0.30

POT

0.30

 Grand

0.29

Bre

0.29

 grand

0.29

out

0.29

 flow

0.29

Activations Density 31.471%

No Known Activations

This feature has no known activations.