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

onaut

-0.28

.setter

-0.27

onna

-0.26

atten

-0.26

otch

-0.25

_syntax

-0.25

umping

-0.24

reten

-0.24

gaard

-0.24

æİ¥åĲ¬

-0.24

POSITIVE LOGITS

ibraries

0.27

è®©æ¶Īè´¹èĢħ

0.26

ÙĬÙĥØ§

0.26

å®½å®¹

0.25

 crowds

0.25

 plug

0.24

lessly

0.24

[min

0.23

ä¸»å®°

0.23

é©¹

0.23

Activations Density 0.053%

No Known Activations

This feature has no known activations.