INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 replacing

-0.25

ãĤ¿ãĥ³

-0.24

ãģŀ

-0.24

ahu

-0.24

demand

-0.24

.gov

-0.23

 projectile

-0.23

ifax

-0.23

input

-0.23

 prompt

-0.23

POSITIVE LOGITS

TEE

0.27

 Beste

0.26

cret

0.26

eds

0.25

cion

0.25

æĹº

0.25

 Explos

0.25

acios

0.24

sez

0.24

æķŀ

0.24

Activations Density 0.822%

No Known Activations

This feature has no known activations.