© 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. 22586
    Prev
    Next
    INDEX
    Explanations

    gradient and derivative terms

    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
    haar
    -0.07
    æį¢æ°Ķ
    -0.06
    åľ°äºļ
    -0.06
    arc
    -0.06
     Coff
    -0.06
     géographique
    -0.06
    رض
    -0.06
    ราà¸ļ
    -0.06
    ä¼ĺåĬ¿äºĴè¡¥
    -0.06
    oma
    -0.06
    POSITIVE LOGITS
    adients
    0.09
    balances
    0.09
     derivative
    0.08
    çŁ¢
    0.08
    gres
    0.08
    aglio
    0.08
    nico
    0.08
     derivatives
    0.07
     imbalance
    0.07
    _derivative
    0.07
    Activations Density 0.005%

    No Known Activations