INDEX

Explanations

standard

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

abin

-0.27

ç¹ģåįİ

-0.25

mant

-0.25

èĤ¡æ°ĳ

-0.25

æ´

-0.24

æ³¯

-0.24

è¿Ń

-0.23

-boy

-0.23

otypical

-0.23

æĶ¶åī²

-0.23

POSITIVE LOGITS

 ALWAYS

0.28

Hint

0.27

too

0.27

 Trust

0.27

 always

0.27

æī§çĿĢ

0.27

 Always

0.26

ificaciÃ³n

0.25

bones

0.25

èįļ

0.25

Activations Density 0.111%

standard

No Comments

No Known Activations