INDEX

Explanations

read

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

llib

-0.32

Ð±ÑĢÐ¸

-0.29

thouse

-0.28

ptest

-0.27

PIO

-0.26

ITH

-0.26

ÅŁÄ±

-0.26

cbd

-0.26

æıĲæ¬¾

-0.25

ighet

-0.25

POSITIVE LOGITS

fare

0.30

read

0.29

ä¸Ģæŀļ

0.29

reading

0.28

ç»ıåħ¸

0.27

éĶ¢

0.26

rev

0.26

åĴĮç¤¾ä¼ļ

0.25

READ

0.25

Fault

0.25

Activations Density 0.000%

read

No Known Activations