INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 comb

-0.25

unger

-0.24

Bin

-0.24

edImage

-0.24

 elevation

-0.24

 Step

-0.24

 Hence

-0.24

å¼łå®¶

-0.24

äººæīįéĺŁä¼į

-0.23

ns

-0.23

POSITIVE LOGITS

:+:

0.27

actable

0.26

èłķ

0.26

@m

0.26

æ··

0.25

á»¬

0.24

è¿ĻäºĽéĥ½æĺ¯

0.24

cee

0.24

ç¬¬ä¸īæĸ¹

0.24

rollo

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.