INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç»Īèº«

-0.29

 Ruiz

-0.27

ORIA

-0.27

éĺ²èħĲ

-0.26

cliffe

-0.26

æĦıåĽ¾

-0.26

guest

-0.25

zew

-0.25

bbb

-0.24

ded

-0.24

POSITIVE LOGITS

inine

0.26

glu

0.26

mund

0.26

åľºæĻ¯

0.25

egal

0.25

 sublist

0.24

 KERNEL

0.24

chine

0.24

kernel

0.24

abis

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.