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

åľĪåŃĲ

-0.25

æĦĪ

-0.25

ķĮ

-0.25

æĶ¹æĪĲ

-0.25

 Intercept

-0.24

_both

-0.24

rschein

-0.24

.pretty

-0.23

Vog

-0.23

è¿ĩå¤§

-0.23

POSITIVE LOGITS

MR

0.30

 IMPLIED

0.25

 ready

0.25

 Grove

0.24

 dojo

0.24

rog

0.24

 shed

0.23

ç¬¬åĽĽ

0.23

 beard

0.23

æĿĲ

0.23

Activations Density 61.182%

No Known Activations

This feature has no known activations.