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

FieldValue

-0.26

æĹĭ

-0.26

endment

-0.26

é¬²

-0.25

 transl

-0.25

è¯ļ

-0.25

EventHandler

-0.25

ä¹¦è®°

-0.25

çħ

-0.24

leys

-0.24

POSITIVE LOGITS

istik

0.27

èĨı

0.27

åĽ½ç½ĳ

0.26

ç¬¬ä¸ĢèĬĤ

0.25

_/

0.25

åıĳåĩº

0.25

initial

0.24

-/

0.24

ogra

0.24

BDS

0.23

Activations Density 51.538%

No Known Activations

This feature has no known activations.