© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19530
    Prev
    Next
    INDEX
    Explanations

    extract data or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĴ®
    -0.06
     pom
    -0.05
    主ãģª
    -0.05
    onis
    -0.05
    ECT
    -0.05
    igers
    -0.05
    èĮĥåĽ´ä¹ĭåĨħ
    -0.05
    ilton
    -0.05
    并åıij
    -0.05
    ÛĮدا
    -0.05
    POSITIVE LOGITS
    elen
    0.07
    Ø®ÙĨ
    0.06
    feuille
    0.06
    Ùħاس
    0.05
    åĤ³è¼¸
    0.05
    лении
    0.05
    asher
    0.05
    IgnoreCase
    0.05
    quete
    0.05
    arme
    0.05
    Activations Density 0.001%

    No Known Activations