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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĹĢ

-0.27

 Prelude

-0.25

thood

-0.25

 maur

-0.24

orm

-0.24

sdl

-0.24

');//

-0.24

 Geoff

-0.24

-round

-0.24

 diplomacy

-0.24

POSITIVE LOGITS

 neutral

0.26

neutral

0.26

_PIN

0.26

Datas

0.25

 datasets

0.25

Neutral

0.25

ä¸ºæ°ĳ

0.24

 complex

0.24

çłĶç©¶ä¸Ńå¿ĥ

0.24

utable

0.24

Activations Density 22.682%

No Known Activations

This feature has no known activations.