INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å·¥å§Ķ

-0.27

ÑİÑĢ

-0.27

ä¸įå®¹

-0.26

bard

-0.25

æľīæľŁ

-0.24

æ¥Ķ

-0.24

berra

-0.23

è¡Ģç®¡

-0.23

raud

-0.23

çļĦè¶ĭåĬ¿

-0.23

POSITIVE LOGITS

èĩªçĶ±

0.27

enger

0.25

å¤ļç§į

0.24

è½´

0.24

æĬķ

0.24

è¾ĳ

0.24

space

0.23

 case

0.23

 axis

0.23

elt

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.