INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

urn

-0.30

 ÑĦÐ°Ð¹

-0.26

æĹłæīĢ

-0.26

æ¾Ħ

-0.25

Tele

-0.24

transform

-0.24

 domin

-0.24

åģĩ

-0.24

è®¹

-0.24

è£Ĥ

-0.23

POSITIVE LOGITS

åĬĽè¿ĺæĺ¯

0.32

å®ŀéĻħæĥħåĨµ

0.29

issance

0.28

tures

0.27

ieurs

0.26

æĹłæīĢè°ĵ

0.26

fortunate

0.25

ï¼ģ↵↵↵↵

0.25

perimental

0.25

fort

0.25

Activations Density 0.113%

No Known Activations

This feature has no known activations.