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

Ann

-0.34

ä¸įå±ŀäºİ

-0.29

Ann

-0.28

 Revel

-0.25

å¹´ä¸ĭåįĬå¹´

-0.25

mp

-0.24

 Sellers

-0.24

 Redistributions

-0.24

laden

-0.24

æĬĢèĥ½

-0.24

POSITIVE LOGITS

.Ui

0.29

è¦Ĩ

0.27

 checked

0.27

checked

0.27

inka

0.26

tti

0.26

 BindingFlags

0.25

éª§

0.25

åŁŁ

0.25

saf

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.