INDEX

Explanations

Features/Offers/Provides

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èıľåįķ

-0.28

æĥ³äºĨ

-0.27

å¤§åĬĽåıĳå±ķ

-0.27

Pik

-0.26

åħ³åĪĩ

-0.26

quirer

-0.25

çļĦåħ³æ³¨

-0.25

çļĦåĬªåĬĽ

-0.25

elf

-0.24

çŃļ

-0.24

POSITIVE LOGITS

 confession

0.26

uestra

0.25

 conf

0.24

æķ¦

0.24

CFG

0.24

ÑĭÐ²Ð°

0.24

 alleg

0.24

itaire

0.23

itizer

0.23

 professionnel

0.23

Activations Density 0.154%

Features/Offers/Provides

No Comments

No Known Activations