© 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. 47138
    Prev
    Next
    INDEX
    Explanations

    Riemann hypothesis

    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
    cz
    -0.09
    irth
    -0.08
    bery
    -0.08
    emming
    -0.08
    leston
    -0.08
    /remove
    -0.08
    quo
    -0.08
    ird
    -0.08
    itez
    -0.07
    ±
    -0.07
    POSITIVE LOGITS
    Ø©
    0.10
    ukung
    0.08
    ÑģÑı
    0.08
    ometer
    0.07
    ical
    0.07
    ÛĮ
    0.07
    al
    0.07
    ä¸įçŁ¥éģĵä½ł
    0.07
    ãģĤãĤĭ
    0.07
    Ùĥ
    0.07
    Activations Density 0.001%

    No Known Activations