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

Negative Logits

ivity

-0.28

roys

-0.28

 Specs

-0.27

 licensors

-0.26

çļĦæĸ¹åĲĳ

-0.26

åŃ£

-0.25

 chac

-0.25

ç¼º

-0.24

èµ°è¿ĳ

-0.24

FO

-0.24

POSITIVE LOGITS

atis

0.29

ç®¡çĲĨä½ĵåĪ¶

0.25

 CENT

0.25

/device

0.24

axon

0.24

EIF

0.24

xAE

0.24

 mÃ¡i

0.23

[array

0.23

zent

0.23

Activations Density 0.011%

No Known Activations

This feature has no known activations.