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

raits

-0.28

efd

-0.27

emin

-0.26

ertas

-0.26

elda

-0.26

sla

-0.26

neh

-0.26

PARATOR

-0.25

efa

-0.25

avings

-0.25

POSITIVE LOGITS

dur

0.27

 lasted

0.27

 endured

0.26

æĶ¶å½ķ

0.26

ç½

0.25

dur

0.25

#error

0.25

oss

0.25

æĢ¨

0.25

åħ¬å®īå±Ģ

0.25

Activations Density 0.049%

No Known Activations

This feature has no known activations.