INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.ai

-0.27

Ai

-0.27

 defender

-0.26

åıĳå±ķä¸Ń

-0.26

æĶ¾å¤§

-0.26

AI

-0.26

ai

-0.25

 Domestic

-0.25

ri

-0.25

Colon

-0.25

POSITIVE LOGITS

ä¿±

0.28

inema

0.28

ErrorException

0.28

lessly

0.27

fires

0.27

yu

0.26

ModuleName

0.26

.datab

0.26

ijd

0.26

ç¨¼

0.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.