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

Not in Any Lists

No Comments

Negative Logits

äº¤æ±ĩ

-0.28

è¯ģåĪ¸äº¤æĺĵ

-0.27

itudes

-0.26

 BaseModel

-0.26

imeters

-0.25

 subdivisions

-0.25

 intersections

-0.25

tracts

-0.24

 jurisdictions

-0.24

 leverage

-0.24

POSITIVE LOGITS

chs

0.32

abel

0.28

è¿Ļäºĭ

0.28

éĢģæĿ¥

0.26

elt

0.25

å¢ŀåĬłäºĨ

0.25

gir

0.25

 chute

0.25

 Changed

0.24

apur

0.24

Activations Density 16.235%

No Known Activations

This feature has no known activations.