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

<![

-0.31

obi

-0.26

assi

-0.26

etty

-0.26

wayne

-0.25

æ²Ļ

-0.25

 bell

-0.25

 Sandbox

-0.24

aura

-0.24

asse

-0.24

POSITIVE LOGITS

 screw

0.31

.sql

0.27

oproject

0.26

ãĥ¼ãĥ«

0.26

 advance

0.25

nah

0.25

è¯Ń

0.25

çĪ±å¥½

0.25

æĺ¯ä¸Ģä¸ª

0.24

å¹¶å¯¹

0.24

Activations Density 0.362%

No Known Activations

This feature has no known activations.