INDEX

Explanations

code and brand names

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

rop

-0.34

ROP

-0.31

é¥®æĸĻ

-0.29

 beverage

-0.29

roe

-0.29

 syrup

-0.28

æ¶²

-0.27

åįĬä¸ªå°ıæĹ¶

-0.27

sten

-0.27

 Beverage

-0.27

POSITIVE LOGITS

dana

0.29

æĥĬ

0.29

ona

0.27

è§ī

0.25

à¸ĩ

0.25

å±Ģ

0.25

athi

0.25

oya

0.25

lections

0.25

ilha

0.25

Activations Density 0.000%

code and brand names

No Comments

No Known Activations