INDEX

Explanations

decoration

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

é³ŀ

-0.27

æĢ§èĥ½

-0.27

ndef

-0.26

æ»¡åĪĨ

-0.25

å¿ĥçĽ®

-0.25

Cit

-0.25

_Interface

-0.25

æĿ°åĩº

-0.24

 defining

-0.24

ApiController

-0.24

POSITIVE LOGITS

åĬª

0.29

èİº

0.28

 period

0.27

ãĥł

0.27

pliers

0.26

Au

0.25

ç³»

0.25

å¸ĥç½®

0.25

 guilty

0.25

allery

0.25

Activations Density 0.017%

decoration

No Comments

No Known Activations