INDEX

Explanations

Technical instructions/explanations

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

edly

-0.27

ymology

-0.25

 OnClickListener

-0.24

unya

-0.24

erge

-0.24

shiv

-0.23

udi

-0.23

forth

-0.23

 onPage

-0.23

 searcher

-0.23

POSITIVE LOGITS

ÑĢÐ¾Ð½

0.28

Zig

0.26

Sco

0.26

åĴĮæĶ¯æĮģ

0.26

é¦ĸ

0.25

Aws

0.25

åĳĬè¯ī

0.25

qing

0.24

haven

0.24

åĳĬè¨´

0.24

Activations Density 0.049%

Technical instructions/explanations

No Comments

No Known Activations