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

.cz

-0.30

 fraction

-0.26

osta

-0.25

.za

-0.25

 minute

-0.25

minute

-0.25

-ring

-0.25

-pe

-0.24

verse

-0.24

\xc

-0.24

POSITIVE LOGITS

_nth

0.28

 valleys

0.27

.getSimpleName

0.26

èĤī

0.24

·¸

0.24

 Strategies

0.24

æļĸæ°Ķ

0.24

 Äĳáº¡i

0.24

NAS

0.24

 theaters

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.