INDEX

Explanations

place names and locations

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

è±Ĳ

-0.28

æ²»

-0.26

.Names

-0.26

.ep

-0.26

inated

-0.25

å®¸

-0.25

ania

-0.25

åħ¬å¼Ģåıĳ

-0.24

vetica

-0.24

ence

-0.24

POSITIVE LOGITS

 Norton

0.26

 Wave

0.26

-wave

0.25

ASN

0.24

ession

0.24

æĢ»çļĦ

0.24

/connect

0.23

 Workbook

0.23

 connect

0.23

 breeze

0.23

Activations Density 0.001%

place names and locations

No Comments

No Known Activations