INDEX

Explanations

vitamin

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__.__

-0.29

ixo

-0.28

imm

-0.28

immune

-0.26

ç¤ºèĮĥåĮº

-0.25

 Sixth

-0.25

phe

-0.25

ijo

-0.24

:convert

-0.24

 Panda

-0.24

POSITIVE LOGITS

ellig

0.28

apt

0.26

ockets

0.25

ook

0.25

unks

0.25

æĽ

0.25

Br

0.25

gle

0.24

åĮĸ

0.24

ad

0.24

Activations Density 0.039%

vitamin

No Comments

No Known Activations