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

metic

-0.28

 Celt

-0.27

åºľ

-0.27

ä¿³

-0.26

gsi

-0.25

äºī

-0.25

 Hier

-0.25

é¡ºåºı

-0.24

ACP

-0.24

ç©º

-0.24

POSITIVE LOGITS

éķ«

0.26

 recognised

0.26

 recognized

0.25

è®£

0.25

 Fargo

0.25

 recognition

0.25

èłķ

0.25

èĤ¡

0.24

 operand

0.24

ç¼Ļ

0.24

Activations Density 4.859%

No Known Activations

This feature has no known activations.