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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18530
    Prev
    Next
    INDEX
    Explanations

    use of your

    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
    iner
    -0.06
    éģ¿
    -0.06
    omot
    -0.06
    StackTrace
    -0.06
    ivan
    -0.06
    rg
    -0.06
    åľ¨æľĢ
    -0.06
     ÛĮاد
    -0.06
    QA
    -0.05
    æĮ¡
    -0.05
    POSITIVE LOGITS
    <typeof
    0.06
    ä»Ģä¹Īåij¢
    0.05
     fellow
    0.05
    ษà¹Į
    0.05
    åħ¶ä»ĸ人çļĦ
    0.05
    æݥ管
    0.05
    人æĿ¥
    0.05
     ÐŀÑģнов
    0.05
    éļĽ
    0.05
     оÑģнова
    0.05
    Activations Density 0.016%

    No Known Activations