INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Unter

-0.28

nip

-0.27

 synt

-0.26

æĬ¼

-0.26

 succeed

-0.25

dau

-0.25

 Murdoch

-0.24

áº¿

-0.24

ollipop

-0.24

 commission

-0.24

POSITIVE LOGITS

cer

0.27

ç¥¥

0.26

 scares

0.26

æ¹Ľ

0.25

 má»Ļ

0.25

æª¬

0.25

æĢħ

0.25

-rad

0.25

ä¸ºä¸Ģä½ĵçļĦ

0.24

gh

0.24

Activations Density 0.844%

No Known Activations

This feature has no known activations.