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

Negative Logits

å°½

-0.26

æĢ»ç®Ĺ

-0.26

 Schiff

-0.25

ITTLE

-0.24

èĩªä¹ł

-0.24

 titan

-0.23

åŁŃ

-0.23

 amount

-0.23

,},↵

-0.23

 fulfilling

-0.23

POSITIVE LOGITS

][/

0.27

dig

0.27

 bÃ¶r

0.26

sy

0.26

ez

0.26

rub

0.25

ç£¨

0.25

ç»´å¥ĩ

0.25

sy

0.25

 gotten

0.25

Activations Density 0.002%

No Known Activations

This feature has no known activations.