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

æīĴ

-0.28

deg

-0.27

åī©ä¸ĭçļĦ

-0.26

åĬ£

-0.26

åı¦ä¸Ģç§į

-0.25

æĭ´

-0.25

imits

-0.25

 vard

-0.24

åı¦å¤ĸ

-0.24

 pans

-0.23

POSITIVE LOGITS

qua

0.28

gue

0.25

rite

0.25

=img

0.24

 Blades

0.24

ioni

0.24

orrh

0.23

éĻ°

0.23

createClass

0.23

 Increment

0.23

Activations Density 0.628%

No Known Activations

This feature has no known activations.