INDEX

Explanations

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

rist

-0.28

ris

-0.28

å°ĳäºĨ

-0.27

äº®çĽ¸

-0.27

 mÃ©

-0.27

çĤ¹äºĨ

-0.26

 Straw

-0.26

å°½

-0.25

.githubusercontent

-0.25

istring

-0.25

POSITIVE LOGITS

 naveg

0.27

Ð¼Ð°ÑĢ

0.26

panion

0.26

 extr

0.25

 grind

0.25

 patterns

0.25

ä¸Ģä¸ªæĸ°çļĦ

0.25

 backyard

0.25

drv

0.25

 pari

0.25

Activations Density 0.073%

punctuation

No Comments

No Known Activations