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

èĽĭ

-0.28

æĭ¦

-0.25

æĸ°éĹ»ç½ĳ

-0.25

 \↵↵

-0.25

 disap

-0.25

 puss

-0.24

sca

-0.24

ACCEPT

-0.23

 Sonia

-0.23

âĬĥ

-0.23

POSITIVE LOGITS

eut

0.27

åı°

0.27

orate

0.26

éĤ®å¯Ħ

0.25

Handled

0.25

alus

0.25

Ju

0.24

ä¼Ĭ

0.24

aval

0.24

 projected

0.24

Activations Density 1.102%

No Known Activations

This feature has no known activations.