© 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. 43418
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
    ivity
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.09
    rene
    -0.09
    rement
    -0.08
    reon
    -0.08
    ockets
    -0.08
    ively
    -0.08
    ENTO
    -0.08
    ors
    -0.08
    olith
    -0.08
    POSITIVE LOGITS
    ey
    0.08
    bé
    0.08
    ÑĮи
    0.08
    ê¹IJ
    0.07
    Ø·ÙĨ
    0.07
    лÑĮÑĦа
    0.07
    yas
    0.07
    roupon
    0.07
    gili
    0.07
    ÑĥÑī
    0.07
    Activations Density 0.286%

    No Known Activations