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

éĹ´éļĶ

-0.28

 metic

-0.27

æ¾³å¤§

-0.27

 Shak

-0.26

å¯¹å¥¹

-0.26

èĽĽ

-0.25

å¯¹ä»ĸ

-0.24

iska

-0.24

ustral

-0.24

 bomb

-0.24

POSITIVE LOGITS

á»ĳng

0.28

ãĥ¬ãĤ¹ãĥĪ

0.26

ende

0.26

%"

0.26

####

0.25

Pee

0.25

bed

0.25

otten

0.24

çħ§æĺİ

0.24

.sleep

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.