INDEX

Explanations

percentage

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 clarify

-0.31

éľĨ

-0.28

emics

-0.28

 clar

-0.28

trigger

-0.26

éĢĨè¡Į

-0.26

æ¾Ħæ¸ħ

-0.25

JOR

-0.25

	trigger

-0.25

ÑģÑĤÐ¾Ð»ÑĮ

-0.24

POSITIVE LOGITS

æľ¬æĬ¥è®¯

0.28

åŃĹç¬¬

0.27

istrator

0.26

##_

0.25

leep

0.24

.webdriver

0.24

atin

0.23

 ReSharper

0.23

{$

0.23

èĦĤèĤª

0.23

Activations Density 0.000%

percentage

No Comments

No Known Activations