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

dim

-0.29

Out

-0.28

 Regression

-0.28

 dims

-0.28

Out

-0.28

cran

-0.27

dims

-0.27

outh

-0.27

/MIT

-0.26

 silenced

-0.26

POSITIVE LOGITS

amarin

0.28

æľīæĿ¡ä»¶çļĦ

0.27

 exercising

0.27

 survives

0.26

 StringBuffer

0.26

eron

0.26

	StringBuffer

0.26

 fetish

0.26

 surviving

0.25

 cigars

0.25

Activations Density 0.004%

of

No Comments

No Known Activations