INDEX

Explanations

of

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\views

-0.26

åĪĺæµ·

-0.26

-hover

-0.25

.nextToken

-0.25

Football

-0.25

è½¬åĲĳ

-0.24

å¼ģ

-0.24

çĤĬ

-0.24

 pools

-0.23

-contained

-0.23

POSITIVE LOGITS

æĸĻ

0.28

 suspect

0.28

da

0.27

sus

0.25

UCT

0.25

ium

0.24

 trá»¥

0.24

æ¡¢

0.24

é¢Ĺ

0.24

ÑģÑĤÐ²

0.24

Activations Density 0.490%

of

No Comments

No Known Activations