INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĬŁ

-0.26

 translators

-0.26

ĳľ

-0.24

../../../

-0.24

-loader

-0.24

ropic

-0.24

è¦ģåİ»

-0.23

steen

-0.23

 invitation

-0.23

 irritating

-0.23

POSITIVE LOGITS

ilos

0.28

andum

0.26

 uniquely

0.26

åĬ²

0.25

å¤§åĽ½

0.25

ihu

0.24

CW

0.24

inions

0.24

ames

0.24

(Collections

0.23

Activations Density 0.185%

No Known Activations

This feature has no known activations.