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

Not in Any Lists

No Comments

Negative Logits

(![

-0.29

 heck

-0.25

<const

-0.24

iar

-0.24

pNet

-0.24

æ¶Īè´¹èĢħ

-0.23

GES

-0.23

æĤŃ

-0.23

éĢ¡

-0.23

¹Ħ

-0.23

POSITIVE LOGITS

è°ı

0.28

äººæł¼

0.27

èĬĤ

0.26

å¤§äºĭ

0.24

AIM

0.23

ç«łç¨ĭ

0.23

áº¡n

0.23

zet

0.23

bal

0.23

Resources

0.22

Activations Density 83.193%

No Known Activations

This feature has no known activations.