© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20686
    Prev
    Next
    INDEX
    Explanations

    both, combined, hybrids, and, mixed

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ORMAL
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    èĨĺ
    -0.08
    agli
    -0.07
    бак
    -0.07
    клик
    -0.07
    ampe
    -0.07
    èŁĨ
    -0.07
    ä¼ĺå¼ĤæĪIJ绩
    -0.07
    aget
    -0.07
    POSITIVE LOGITS
    äºĮèĢħ
    0.11
    两èĢħ
    0.10
     keduanya
    0.09
     بÙĬÙĨÙĩÙħا
    0.08
    è¿Ļ两ç§į
    0.08
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    0.08
    åħ©èĢħ
    0.07
    orts
    0.07
    è´
    0.07
    combe
    0.07
    Activations Density 0.066%

    No Known Activations