© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21521
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñģл
    -0.08
    ained
    -0.08
    gewater
    -0.07
    arin
    -0.07
    aining
    -0.07
    æłĦ
    -0.07
    anoia
    -0.07
    queira
    -0.07
    Ĥ¬
    -0.07
    lington
    -0.07
    POSITIVE LOGITS
    raud
    0.07
    èĴĤæĸ¯
    0.07
    ãģĿ
    0.07
    اردة
    0.07
    ìĨ¡
    0.07
    ัà¸ģษà¹Į
    0.06
    portiva
    0.06
    èque
    0.06
    Ń
    0.06
    å¾Ĺä½ı
    0.06
    Activations Density 0.000%

    No Known Activations