© 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. 56609
    Prev
    Next
    INDEX
    Explanations

    real numbers and integers

    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
    é«ĺä½İ
    -0.07
    ostro
    -0.06
    nam
    -0.06
    ueill
    -0.06
    使çĶ¨ä¸Ń
    -0.06
    .capture
    -0.06
    åĴĮèĥ½åĬĽ
    -0.06
     Alm
    -0.06
     bỼt
    -0.06
    est
    -0.06
    POSITIVE LOGITS
    emani
    0.10
    Sharper
    0.08
    Convertible
    0.08
     sayısı
    0.07
    _tuples
    0.07
    atum
    0.07
    ürg
    0.07
    emet
    0.07
    /black
    0.07
    importe
    0.07
    Activations Density 0.035%

    No Known Activations