INDEX

Explanations

start or end

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éħ¿

-0.28

åĻ¨

-0.28

çĽĪ

-0.26

èķĥ

-0.25

jian

-0.24

.poll

-0.24

èĢĮå¯¹äºİ

-0.24

æīĢæīĢ

-0.24

è¿«ä½¿

-0.23

ç§ģ

-0.23

POSITIVE LOGITS

 emerges

0.35

 emerge

0.30

 arises

0.27

ä½ľèĢħæľ¬äºº

0.25

 Caption

0.25

 Bullet

0.24

orial

0.24

 there

0.24

uther

0.24

there

0.24

Activations Density 0.002%

start or end

No Comments

No Known Activations