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

æľĲ

-0.27

åĿļåĽº

-0.26

chia

-0.26

uling

-0.25

 incumb

-0.25

uy

-0.25

xab

-0.24

åĶĨ

-0.24

oder

-0.23

uci

-0.23

POSITIVE LOGITS

 Guaranteed

0.25

/twitter

0.24

 repositories

0.24

 guarante

0.24

lew

0.24

OLUTE

0.24

å½ĵä¹ĭ

0.23

ogui

0.23

 Dort

0.23

ãĤĩ

0.23

Activations Density 0.009%

No Known Activations

This feature has no known activations.