INDEX

Explanations

7

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

æĭŃ

-0.33

 Parad

-0.26

imer

-0.26

vm

-0.25

ugs

-0.24

 parad

-0.24

æĬ¹

-0.24

Vul

-0.24

seek

-0.24

sd

-0.24

POSITIVE LOGITS

.IsValid

0.27

æ¬¡ä¼ļè®®

0.25

ifa

0.24

iera

0.24

åĨ³å®ļäºĨ

0.24

 benches

0.24

.hr

0.24

--,

0.24

issan

0.24

 tasked

0.23

Activations Density 0.002%

7

No Comments

No Known Activations