INDEX

Explanations

Ed

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

æľŁåĨħ

-0.29

æĭ§

-0.28

turnstile

-0.26

æĪĲäºº

-0.26

 sprung

-0.25

 scares

-0.25

ç½ĳè®¯

-0.24

Dice

-0.24

optic

-0.24

dale

-0.24

POSITIVE LOGITS

 aque

0.29

pta

0.28

åĮĸåŃ¦

0.27

 chemistry

0.26

çĩĥæĸĻ

0.26

 chemical

0.25

petition

0.25

enic

0.25

chemistry

0.25

éĴĮ

0.25

Activations Density 0.027%

Ed

No Comments

No Known Activations