INDEX

Explanations

say ")"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

:System

-0.26

è¡ĮæĶ¿å®¡æī¹

-0.25

æ¨Ļ

-0.24

 autoc

-0.24

 Wikipedia

-0.24

æ»ĩ

-0.24

åªļ

-0.23

åº¶

-0.23

 íĳľ

-0.23

 advers

-0.23

POSITIVE LOGITS

ording

0.32

åĽŀæĿ¥

0.29

agine

0.28

æıŃ

0.27

ardless

0.27

0.26

ulan

0.26

agraph

0.25

éļĶ

0.25

Activations Density 0.006%

say ")"

No Known Activations