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

 forwards

-0.26

 backward

-0.26

 cosmos

-0.25

urar

-0.25

iesel

-0.25

urf

-0.25

 backwards

-0.24

CTOR

-0.24

AdapterManager

-0.24

çĽ®çļĦ

-0.24

POSITIVE LOGITS

çķĻ

0.29

imeo

0.28

Leave

0.28

é«¹

0.26

à¹Ģà¸Ĺ

0.26

 Leave

0.26

å¾½

0.25

Arthur

0.25

 carr

0.25

ption

0.25

Activations Density 0.175%

No Known Activations

This feature has no known activations.