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

æ±¡

-0.28

refer

-0.26

 expectancy

-0.26

 tall

-0.25

aside

-0.25

 scaffold

-0.24

uses

-0.23

 were

-0.23

portlet

-0.23

 refer

-0.23

POSITIVE LOGITS

èĽĶ

0.27

åĲİæŀľ

0.27

SSION

0.26

ç¦ģ

0.26

indr

0.25

ç©¶

0.23

BTN

0.23

åº¦

0.23

ä½¯

0.23

 zeigt

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.