© 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. 32066
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    pret
    -0.06
     unin
    -0.06
    çļĦå¿ĥèĦı
    -0.06
    ulang
    -0.06
    ÑĨо
    -0.06
    ä¸ĭæĸ¹äºĮç»´çłģ
    -0.06
    yl
    -0.06
    quo
    -0.06
    aeda
    -0.06
    assy
    -0.06
    POSITIVE LOGITS
    ancies
    0.09
    ÙĪا
    0.08
    _totals
    0.08
    tings
    0.08
    iless
    0.08
    ughters
    0.08
    les
    0.08
    hazi
    0.07
    -exclusive
    0.07
    ÙĪبات
    0.07
    Activations Density 0.005%

    No Known Activations