INDEX

Explanations

Computer instructions

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

.addAttribute

-0.28

nh

-0.27

èĢģ

-0.27

 flooding

-0.26

æķ´ä½ĵ

-0.25

nes

-0.25

çŁ¥è¯Ĩ

-0.24

åĪĨåī²

-0.24

Ø¨Ø§Ø±Ùĥ

-0.24

POSITIVE LOGITS

acf

0.27

 chambers

0.25

æĮ¯ãĤĬ

0.25

seo

0.25

 thankful

0.25

/repos

0.24

 regrets

0.24

µ¬

0.24

å¾ĹæĦı

0.24

 overst

0.23

Activations Density 0.009%

Computer instructions

No Comments

No Known Activations