INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

à¹ģà¸Ļ

-0.26

à¸¨à¸²à¸ª

-0.25

 tÃ¡n

-0.25

 unit

-0.25

 Bounds

-0.24

 Markets

-0.24

 Downing

-0.24

sty

-0.24

è¿Ķä¹¡

-0.23

queeze

-0.23

POSITIVE LOGITS

ubs

0.26

åıĳå±ķç©ºéĹ´

0.26

 flour

0.25

.rl

0.25

/entities

0.25

èµ°

0.24

äºĴéĢļ

0.24

 Truyá»ģn

0.24

 Joined

0.24

 gháº¿

0.23

Activations Density 2.889%

No Known Activations

This feature has no known activations.