INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ITTER

-0.28

itter

-0.27

bury

-0.26

zÄħ

-0.25

åģ¥åº·çļĦ

-0.25

.connect

-0.25

æĺİå¹´

-0.24

AtPath

-0.24

 tips

-0.24

å°Ĩä»¥

-0.23

POSITIVE LOGITS

(~(

0.26

letal

0.26

regn

0.26

èŃ¦

0.26

ration

0.25

 ê·¸ëłĩì§Ģ

0.25

lesi

0.24

èįª

0.24

åħ°

0.24

åĨ²

0.24

Activations Density 12.784%

No Known Activations

This feature has no known activations.