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

quil

-0.26

tim

-0.26

iming

-0.26

é£İ

-0.26

åĪĩãĤĬ

-0.25

 helm

-0.23

äº§åĩº

-0.23

ACHI

-0.23

xf

-0.23

xF

-0.23

POSITIVE LOGITS

zia

0.26

ounder

0.25

ublish

0.24

ÑģÑı

0.24

.cum

0.24

BUG

0.24

oods

0.23

è¿ĩéĶĻ

0.23

UBLISH

0.23

 states

0.23

Activations Density 0.128%

No Known Activations

This feature has no known activations.