© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    vector algebra

    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
    ulina
    -0.09
    èĮ¶æ°´
    -0.08
    çļĦç§įåŃIJ
    -0.08
    acking
    -0.07
    ä¸ºåĽ½
    -0.07
    oplevel
    -0.07
    FileSize
    -0.07
     trickle
    -0.07
    æĸĩ件大å°ı
    -0.07
    oraf
    -0.07
    POSITIVE LOGITS
    çŁ¢éĩı
    0.11
     vectors
    0.11
     vector
    0.10
     Vector
    0.10
    Vectors
    0.09
    vecs
    0.08
    .vector
    0.08
    vector
    0.08
    Vector
    0.08
    -vector
    0.08
    Activations Density 0.009%

    No Known Activations