INDEX

Explanations

numbers

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

lags

-0.29

ä½ıäºĨ

-0.27

_literals

-0.25

é£İæļ´

-0.25

ISI

-0.25

 honeymoon

-0.24

 arrange

-0.24

 Ahead

-0.24

OOT

-0.24

Ð½Ð¸ÑĨ

-0.24

POSITIVE LOGITS

é¡¹

0.31

ä¸įç¦ģ

0.28

 Philippe

0.26

å¤Ħæĸ¹

0.25

vie

0.25

ä¸įåħį

0.25

å¸¦

0.25

dac

0.24

å¤ļé¡¹

0.23

 corner

0.23

Activations Density 0.047%

numbers

No Comments

No Known Activations