INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éħįä¸Ĭ

-0.29

omination

-0.27

ä½łè¿ĺ

-0.25

acco

-0.25

 educated

-0.24

æĮĩå¯¼æĦıè§ģ

-0.24

æī¹æ¬¡

-0.24

åĬłä¹ĭ

-0.24

.Directory

-0.24

 Ð»Ð¸ÑĤ

-0.23

POSITIVE LOGITS

(engine

0.26

eki

0.26

-track

0.26

ran

0.26

veal

0.24

eva

0.24

.onStart

0.24

åĬŁèĥ½æĢ§

0.24

nosti

0.23

çĩĥ

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.