INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CHARSET

-0.27

æ³Ĳ

-0.25

orsk

-0.25

undles

-0.24

ftype

-0.24

ä¸Ģç»Ħ

-0.24

 topo

-0.24

 iota

-0.24

 puss

-0.23

acity

-0.23

POSITIVE LOGITS

 Trom

0.30

preneur

0.28

cum

0.27

Wo

0.26

-seeking

0.25

ipient

0.24

fur

0.24

 aÃ§Ä±sÄ±ndan

0.24

rib

0.24

inged

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.