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

,&

-0.27

poon

-0.26

æŀĭ

-0.25

alink

-0.24

rossover

-0.24

 hint

-0.23

å»Ĭ

-0.23

"My

-0.23

 Individual

-0.23

“My

-0.23

POSITIVE LOGITS

æĢ§å¼º

0.27

Crypt

0.27

 crypt

0.26

crypt

0.26

 fresh

0.26

man

0.25

Ð½ÑıÑĤÐ¸

0.25

 pulp

0.25

fresh

0.25

ÙĨØ¹

0.24

Activations Density 0.016%

No Known Activations

This feature has no known activations.