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

çº¡

-0.28

ç©ºçĻ½

-0.27

 expl

-0.25

 track

-0.25

è¿Ļä»½

-0.25

 gamm

-0.24

PropertyParams

-0.24

ðŁĺħ

-0.24

 experimenting

-0.24

SSP

-0.23

POSITIVE LOGITS

æĺ¯åĽ½åĨħ

0.25

 Towers

0.25

 registers

0.25

Ø´Ø¹Ø§Ø±

0.25

å°±å¾Ĺ

0.25

å¥

0.25

 vows

0.25

alon

0.24

ackson

0.24

(_,

0.24

Activations Density 0.005%

No Known Activations

This feature has no known activations.