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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abble

-0.28

(counter

-0.27

 Transit

-0.26

èĤ¥

-0.26

æ³ª

-0.26

]){

-0.25

 Counter

-0.25

counter

-0.25

 counter

-0.24

Counter

-0.24

POSITIVE LOGITS

estring

0.27

glo

0.26

åħ¥å¸Ĥ

0.26

æİ§

0.26

EGA

0.26

 volunteering

0.26

 backstory

0.26

 preseason

0.26

ç½ĳç«Ļåľ°åĽ¾

0.26

	Register

0.25

Activations Density 0.018%

No Known Activations

This feature has no known activations.