INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

çļĦåīįæıĲä¸ĭ

-0.29

æĿ¡ä»¶ä¸ĭ

-0.28

vis

-0.26

ãĤŃãĥ¥

-0.26

vg

-0.25

èĻļç©º

-0.25

vis

-0.25

 overload

-0.24

compress

-0.24

 dimensions

-0.24

POSITIVE LOGITS

 Rockefeller

0.29

 resil

0.27

oya

0.26

 fert

0.25

ocrats

0.25

ä¸Ģèĩ´æĢ§

0.25

SHOT

0.24

 Dá»±

0.24

acons

0.24

erah

0.24

Activations Density 0.110%

No Known Activations

This feature has no known activations.