INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Treatment

-0.27

feat

-0.26

Treatment

-0.26

åĸĻ

-0.25

Ã©rc

-0.24

pressive

-0.24

.localized

-0.24

çĨŁ

-0.23

AutoSize

-0.23

æĴŀåĩ»

-0.23

POSITIVE LOGITS

 Neutral

0.30

 neutral

0.29

 parallel

0.28

ais

0.27

 neutrality

0.27

fr

0.26

pr

0.25

ockets

0.25

 beta

0.25

æĿı

0.25

Activations Density 1.681%

No Known Activations

This feature has no known activations.