© 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. 62944
    Prev
    Next
    INDEX
    Explanations

    case-control study

    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
    iep
    -0.08
    umah
    -0.07
    aps
    -0.07
    iele
    -0.07
    éĺij
    -0.07
    icip
    -0.07
     Figu
    -0.07
    zieh
    -0.07
    olated
    -0.06
     Fant
    -0.06
    POSITIVE LOGITS
    éģ¨
    0.07
    æĥħæĦı
    0.07
    antal
    0.07
    rette
    0.07
    Ùħرة
    0.06
    eldorf
    0.06
    áĢ²
    0.06
     блоге
    0.06
    èĤ¥
    0.06
    quier
    0.06
    Activations Density 0.005%

    No Known Activations