INDEX

Explanations

research texts

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

Fans

-0.31

 subscribed

-0.31

 hospitalized

-0.30

 Mater

-0.28

entine

-0.28

 Fans

-0.28

 mater

-0.28

 ReactDOM

-0.27

olen

-0.27

dea

-0.27

POSITIVE LOGITS

æĺ¯ä¸įåı¯èĥ½

0.27

ä¸ºæĤ¨

0.26

 ..."↵↵

0.26

ä¹ħä¹ħ

0.25

.shape

0.25

 presents

0.24

 apresent

0.24

ä¸ºä½ł

0.24

ä¸ºå®¢æĪ·

0.24

ÙĤÙĬÙĤ

0.24

Activations Density 0.013%

research texts

No Comments

No Known Activations