© 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. 4001
    Prev
    Next
    INDEX
    Explanations

    new instance of a class

    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
    onton
    -0.08
    ulto
    -0.08
     rê
    -0.08
    escu
    -0.07
    kens
    -0.07
    inese
    -0.07
     Fertig
    -0.07
    azza
    -0.07
    onti
    -0.07
    ITES
    -0.07
    POSITIVE LOGITS
     {}
    0.07
    оÑģÑĮ
    0.07
     solche
    0.07
    oseb
    0.07
    []
    0.06
    _cast
    0.06
    èĬ±
    0.06
     solchen
    0.06
    {}
    0.06
    дал
    0.06
    Activations Density 0.041%

    No Known Activations