INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

igned

-0.28

pra

-0.26

æ·ĸ

-0.26

pie

-0.24

İ·

-0.23

(upload

-0.23

ä¸įéĶĻ

-0.22

âĸ¾

-0.22

ankan

-0.22

.IC

-0.22

POSITIVE LOGITS

éĩĩ

0.35

rone

0.29

thro

0.28

æłĩå¿Ĺ

0.28

dry

0.25

æģ¤

0.25

 Experience

0.23

 install

0.23

 rare

0.23

 doubles

0.23

Activations Density 2.483%

No Known Activations

This feature has no known activations.