INDEX

Explanations

-European

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

POS

-0.29

pos

-0.28

 Instit

-0.27

Tee

-0.27

gro

-0.26

ould

-0.26

(Pos

-0.26

pos

-0.26

ë¡ł

-0.26

Ã©e

-0.24

POSITIVE LOGITS

æĸ¹å¼ıè¿Ľè¡Į

0.25

variants

0.25

 Laurent

0.24

draft

0.24

 READY

0.24

 Lambert

0.23

lichen

0.23

çĩ¥

0.23

èİĵ

0.23

åįıè°ĥ

0.23

Activations Density 0.003%

-European

No Comments

No Known Activations