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

holm

-0.32

-mouth

-0.26

hani

-0.26

idak

-0.26

azÄĥ

-0.25

 varargin

-0.25

ç²¼

-0.24

çľĭå¥½

-0.24

+:+

-0.24

ilestone

-0.24

POSITIVE LOGITS

ickness

0.28

RestController

0.26

reve

0.26

è¢«æīĵ

0.25

èľķ

0.25

ÑģÐ»ÑĥÐ¶

0.25

åħ¨æĺ¯

0.25

Ð¿Ð¾ÑĤ

0.25

çĭ®åŃĲ

0.25

æ´»çĿĢ

0.24

Activations Density 2.443%

No Known Activations

This feature has no known activations.