© 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. 45807
    Prev
    Next
    INDEX
    Explanations

    dot product, vectors, cosine

    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
    ForResource
    -0.08
    _exceptions
    -0.08
    檻
    -0.08
    缺货
    -0.08
    οÏĢ
    -0.08
     ë©ĶìĿ´
    -0.08
    æ§Ľ
    -0.07
    witch
    -0.07
     émission
    -0.07
    ALLOC
    -0.07
    POSITIVE LOGITS
     dot
    0.08
     vector
    0.08
     Vector
    0.08
     cosine
    0.07
     Dot
    0.07
    Dot
    0.07
    .Flags
    0.07
    elve
    0.07
     vectors
    0.07
    Lite
    0.07
    Activations Density 0.008%

    No Known Activations