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

å¥¹è¯´

-0.26

plotlib

-0.26

Dismiss

-0.26

ypi

-0.25

iphy

-0.25

estone

-0.24

 Certain

-0.24

GBT

-0.24

åħ·

-0.24

åĪĩ

-0.24

POSITIVE LOGITS

fur

0.29

 round

0.27

à¸§à¸£

0.26

 referee

0.25

ead

0.25

ve

0.25

æīįæľī

0.24

æĹ¶æĬ¥

0.23

ace

0.23

round

0.23

Activations Density 1.824%

No Known Activations

This feature has no known activations.