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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç§ĥ

-0.27

 permanently

-0.26

exas

-0.26

ridge

-0.26

 neutral

-0.26

 wings

-0.26

 flatt

-0.26

neutral

-0.25

ODO

-0.25

 gracefully

-0.24

POSITIVE LOGITS

.findIndex

0.30

 Aires

0.29

-shell

0.28

å®¢æĪ·çļĦ

0.25

-ts

0.25

å·¥ç¨ĭæĸ½å·¥

0.25

åĽ¢ä½ĵ

0.25

å®¢æĪ·éľĢæ±Ĥ

0.25

åĳ¨æľŁ

0.25

 vess

0.25

Activations Density 0.006%

No Comments

No Known Activations