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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stere

-0.29

 magnetic

-0.28

åĬ¡

-0.27

ery

-0.27

çĤ¹

-0.27

 explosions

-0.27

ARS

-0.26

ersh

-0.26

 Magnetic

-0.26

 Chambers

-0.26

POSITIVE LOGITS

 ulus

0.28

egis

0.27

ãĤĭãĤĤãģ®

0.26

loo

0.26

çĿ£

0.26

.LayoutParams

0.25

ëĭ¬

0.25

asses

0.25

isses

0.25

ileo

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.