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

imps

-0.29

ti

-0.28

tie

-0.28

ownt

-0.27

-sale

-0.25

imp

-0.25

æĸ¹éĿ¢çļĦ

-0.24

dao

-0.24

sale

-0.24

 rece

-0.24

POSITIVE LOGITS

Ð½Ð°Ñĩ

0.32

(bus

0.30

 Free

0.26

Try

0.26

(DBG

0.26

 Plain

0.25

Un

0.25

(utf

0.25

 Guess

0.24

egg

0.24

Activations Density 1.749%

No Known Activations

This feature has no known activations.