INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otive

-0.24

iki

-0.23

iforn

-0.23

 cere

-0.23

æĸĳæĸĵ

-0.23

 conceivable

-0.23

ifes

-0.23

_argv

-0.23

çĨ

-0.23

.ToolTip

-0.23

POSITIVE LOGITS

Liu

0.25

Subscriber

0.24

 trump

0.23

nette

0.23

tres

0.23

>(()

0.23

rador

0.23

ÙĪÙī

0.23

edException

0.23

ompiler

0.22

Activations Density 19.156%

No Known Activations

This feature has no known activations.