INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enger

-0.24

ç¼¢

-0.24

toc

-0.24

.TO

-0.24

unc

-0.23

æĭīæĸ¯

-0.23

Ri

-0.23

 scarce

-0.23

éķ¿çĽ¸

-0.23

 probabil

-0.23

POSITIVE LOGITS

å¹ħåº¦

0.29

 getline

0.28

ä¸ľè·¯

0.27

leh

0.26

 viewers

0.26

éŁª

0.25

getline

0.25

amed

0.25

andal

0.25

indsight

0.24

Activations Density 1.224%

No Known Activations

This feature has no known activations.