INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸±à¸ª

-0.28

isses

-0.27

Suit

-0.26

(Cs

-0.26

/tests

-0.25

[Test

-0.25

 Naming

-0.25

çıī

-0.24

Mic

-0.24

é£İ

-0.24

POSITIVE LOGITS

ativ

0.28

 Mandela

0.26

 tram

0.25

udi

0.25

æĢ¥

0.25

èį¡

0.23

 bear

0.23

ãģ¡ãĤī

0.23

ric

0.23

 Direct

0.23

Activations Density 0.183%

No Known Activations

This feature has no known activations.