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

akan

-0.27

éĤ¸

-0.27

zij

-0.26

ISTRY

-0.25

ried

-0.25

 Dien

-0.24

Vij

-0.24

èĬ±äºĨ

-0.24

 gord

-0.23

tx

-0.23

POSITIVE LOGITS

-Allow

0.25

å¥Ń

0.24

ãĥ¼ãĥ³

0.24

unny

0.24

lo

0.23

å§Ķåĳĺä¼ļ

0.23

illo

0.23

cher

0.23

åĮĸåĲĪ

0.23

aker

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.