INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lif

-0.27

æ¹Ķ

-0.25

åĹª

-0.25

ä¸¾

-0.25

ddf

-0.24

 fist

-0.24

ä¸Ģæľ¬ä¹¦

-0.24

å¤±èĲ½

-0.23

#:

-0.23

icher

-0.23

POSITIVE LOGITS

åĽļ

0.26

FLAGS

0.25

ĸī

0.24

è¿Ħ

0.24

ì

0.24

å°¼æĸ¯

0.23

 wards

0.23

 Trá»įng

0.23

 Unity

0.23

ivamente

0.23

Activations Density 4.693%

No Known Activations

This feature has no known activations.