INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-sector

-0.28

 Nolan

-0.28

 sectors

-0.27

 whole

-0.25

Sector

-0.25

è¡Įä¸ļçļĦ

-0.24

Tw

-0.24

 Sector

-0.23

æĹłå¥Ī

-0.23

åº¹

-0.23

POSITIVE LOGITS

(choice

0.30

panse

0.29

apas

0.28

.choice

0.27

èĤī

0.26

åľ°çĲĥä¸Ĭ

0.26

èĭĩ

0.26

æĺ¼

0.25

åħ¬å¸ĥ

0.25

 Hidden

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.