INDEX

Explanations

gibberish with punctuation

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

Completion

-0.30

éħª

-0.26

èĬ±æł·

-0.26

æī³

-0.25

/hash

-0.25

èĤ¥

-0.25

.AddField

-0.24

zb

-0.24

ien

-0.24

yyyyMMdd

-0.24

POSITIVE LOGITS

 gÃ³i

0.28

inct

0.27

[][

0.27

åħįè´£å£°æĺİ

0.26

èŃ¦åĬ¡

0.26

æĶ¿åºľéĩĩè´Ń

0.25

åĮħè¢±

0.24

pac

0.24

//!

0.24

è¯±æĥĳ

0.24

Activations Density 0.003%

gibberish with punctuation

No Comments

No Known Activations