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

Not in Any Lists

No Comments

Negative Logits

:System

-0.28

å¤§å®¶åĪĨäº«

-0.28

åįĬä¸ª

-0.26

ï¿½t

-0.25

yles

-0.25

isko

-0.25

crest

-0.24

RESH

-0.24

-parts

-0.23

ucc

-0.23

POSITIVE LOGITS

åĬ¨æĳĩ

0.29

 surg

0.28

çļĦç¡®

0.27

æĤī

0.27

 Ð¼Ð¾Ð³

0.26

Env

0.26

 might

0.25

æĹ»

0.25

æ°Ķè´¨

0.25

uro

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.