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

ulet

-0.29

meter

-0.27

SURE

-0.27

Ð¸ÑĤÐµÐ»

-0.26

æº±

-0.25

.SetString

-0.25

è¶ħçº§

-0.25

fÃ©

-0.25

.super

-0.24

å¾Ģå¤ĸ

-0.24

POSITIVE LOGITS

éĢļ

0.26

 Advisor

0.26

 scenario

0.25

èµ¤

0.25

 McCorm

0.25

åħī

0.25

æĢĿæĥ³

0.25

 strategies

0.25

 Trend

0.24

 advise

0.24

Activations Density 41.693%

No Known Activations

This feature has no known activations.