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

Ups

-0.27

 distinct

-0.26

.AutoField

-0.25

 choc

-0.25

åŃ

-0.25

kuk

-0.24

âı

-0.24

forms

-0.23

 protagon

-0.23

===↵

-0.22

POSITIVE LOGITS

ripper

0.28

naire

0.26

 refere

0.25

éĿ¢åħ·

0.24

 Rule

0.24

arp

0.23

---

0.23

æ·¤

0.23

miss

0.23

 -----

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.