INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 chip

-0.29

 direct

-0.24

imations

-0.24

 expressed

-0.24

scr

-0.24

 Bounty

-0.24

 culmination

-0.24

LERÄ°

-0.23

ry

-0.23

sr

-0.23

POSITIVE LOGITS

ophobic

0.30

ildo

0.28

ropolitan

0.27

ocator

0.26

 mobs

0.26

endra

0.25

.defaultValue

0.24

NavController

0.24

eca

0.24

ecd

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.