INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¾¼ãģ¿

-0.29

 influx

-0.29

Knowledge

-0.27

ernote

-0.26

 Demp

-0.24

çģ«çĥ§

-0.24

conexion

-0.24

IfExists

-0.24

 blas

-0.24

ickest

-0.24

POSITIVE LOGITS

formed

0.32

 formed

0.27

OPS

0.25

 spotting

0.25

igen

0.25

æķ´

0.24

APS

0.24

Ø¹Ø±Ø¨

0.24

pare

0.24

ged

0.24

Activations Density 0.124%

No Known Activations

This feature has no known activations.