© 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. 27801
    Prev
    Next
    INDEX
    Explanations

    prime factors of a number

    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
    åįłåĪ°
    -0.07
    èľĴ
    -0.07
    åķ¡
    -0.07
    å¥Ĺ
    -0.07
    éĩijé¦Ļ
    -0.07
     Dix
    -0.07
    CAP
    -0.07
     []*
    -0.07
     franca
    -0.07
    ảnh
    -0.07
    POSITIVE LOGITS
     numberWith
    0.08
    à§įবর
    0.08
     Vul
    0.08
    æĢ»åĢ¼
    0.08
    ATIV
    0.07
     vul
    0.07
    .valueOf
    0.07
    è¿ŀåŁİ
    0.07
     Seconds
    0.07
    evat
    0.07
    Activations Density 0.033%

    No Known Activations