INDEX

Explanations

nominations

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

mente

-0.31

èµİ

-0.30

åĭŁ

-0.27

 pricey

-0.26

áº»

-0.26

ewise

-0.26

 volunteer

-0.25

 volunt

-0.25

 tape

-0.24

itim

-0.24

POSITIVE LOGITS

ä¹¾

0.28

_radi

0.28

species

0.26

å¯¹ä¸ŃåĽ½

0.25

ç®«

0.25

ä¿Ħ

0.25

 Species

0.25

pection

0.24

ä¸Ģå®¶äºº

0.23

è¿Ļå®¶ä¼Ļ

0.23

Activations Density 0.006%

nominations

No Comments

No Known Activations