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

IFrame

Link

Negative Logits

pany

-0.37

 Royale

-0.26

åľºåĲĪ

-0.26

ritz

-0.25

è¹

-0.24

vac

-0.24

.vo

-0.24

åĮ»ç§ĳ

-0.24

ory

-0.24

arial

-0.24

POSITIVE LOGITS

äº¤

0.27

åĢ¾

0.24

croll

0.24

 Brunswick

0.23

CHA

0.23

è¿ĺè®°å¾Ĺ

0.23

ellen

0.23

_prefix

0.23

-than

0.23

éĨĴ

0.23

Activations Density 0.007%

No Known Activations

This feature has no known activations.