INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é³ı

-0.27

bolt

-0.26

èĬĻ

-0.25

icopt

-0.24

includes

-0.24

owel

-0.23

Ð¾Ð¾ÑĢÑĥÐ¶

-0.23

ivent

-0.23

ä¸įåľ¨ä¹İ

-0.23

etter

-0.23

POSITIVE LOGITS

subcategory

0.30

#@

0.25

ashi

0.25

å½ķ

0.24

 impuls

0.24

 prÃªt

0.24

’aut

0.24

à¹Ħà¸§

0.24

çļĦä¸Ģç§į

0.24

])[

0.24

Activations Density 38.311%

No Known Activations

This feature has no known activations.