INDEX

Explanations

domestic

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

 recip

-0.27

eton

-0.27

 daylight

-0.25

ç£ģ

-0.25

/V

-0.25

çŁ¢

-0.25

@class

-0.24

 desar

-0.24

æ°¸è¿ľ

-0.24

 Across

-0.24

POSITIVE LOGITS

ç²Ł

0.29

èĩ³æĸ¼

0.27

èĩ³äºİ

0.27

 compositions

0.26

 Emin

0.26

åĵģç§į

0.26

jis

0.26

gba

0.26

athed

0.24

Objective

0.24

Activations Density 0.040%

domestic

No Comments

No Known Activations