INDEX

Explanations

code/programming

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

olon

-0.28

 emitting

-0.28

 Emit

-0.28

å°±çŁ¥éģĵ

-0.27

reach

-0.27

ãĤ²

-0.26

èİº

-0.25

å®¶éķ¿ä»¬

-0.25

 favors

-0.24

))}↵

-0.23

POSITIVE LOGITS

 lighter

0.28

etros

0.26

 natural

0.26

 heavier

0.26

çģ°å°ĺ

0.24

 encontrado

0.23

 understandable

0.23

rs

0.23

Ste

0.23

DataAdapter

0.23

Activations Density 0.003%

code/programming

No Comments

No Known Activations