© 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. 42830
    Prev
    Next
    INDEX
    Explanations

    SVM classification and learning

    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
    -tabs
    -0.08
    常ä½ı人åı£
    -0.08
    æ¨Ł
    -0.08
    _warnings
    -0.07
    tabs
    -0.07
    å½ķå¾Ĺ
    -0.07
    -repeat
    -0.07
    pane
    -0.07
    Dyn
    -0.07
    ansom
    -0.07
    POSITIVE LOGITS
     learned
    0.09
     learning
    0.09
     Learning
    0.09
     SVM
    0.09
    åŃ¦ä¹ł
    0.08
    ç¥ŀç»ı
    0.08
     Classifier
    0.08
     classifier
    0.08
    éĢļè¿ĩåŃ¦ä¹ł
    0.08
     обÑĥÑĩ
    0.08
    Activations Density 0.025%

    No Known Activations