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

Not in Any Lists

No Comments

Negative Logits

å¡Ķ

-0.37

è¯¾

-0.28

åĤ¨èĵĦ

-0.26

itamin

-0.25

 expense

-0.25

TS

-0.25

 lessons

-0.25

 lesson

-0.25

èĭĶ

-0.25

çĹ°

-0.24

POSITIVE LOGITS

æīĭèĦļ

0.29

åľ°æĸ¹æĶ¿åºľ

0.27

(Il

0.26

(Db

0.26

å·²ä¹ħ

0.26

okit

0.25

ayed

0.25

å·´åŁº

0.24

mis

0.24

ldb

0.24

Activations Density 0.008%

No Known Activations

This feature has no known activations.