INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Retrie

-0.26

(console

-0.26

 moth

-0.25

ÄŁ

-0.25

 transcription

-0.25

 Transcript

-0.25

 crem

-0.25

pees

-0.24

éģģ

-0.24

console

-0.24

POSITIVE LOGITS

erness

0.25

çłĤæµĨ

0.25

èħ¿

0.24

åŁł

0.24

ç²Ĵ

0.24

 Lime

0.24

 Bayer

0.23

essim

0.23

çīĩåŃĲ

0.23

çĴ§

0.23

Activations Density 23.655%

No Known Activations

This feature has no known activations.