© 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. 34149
    Prev
    Next
    INDEX
    Explanations

    prime numbers and powers

    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
    æĩ¿
    -0.07
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
     Leite
    -0.07
    èį¨
    -0.07
    è¢«æŁ¥
    -0.07
     stockholm
    -0.07
    çķªç¦º
    -0.07
    glomer
    -0.07
     paris
    -0.06
    ocache
    -0.06
    POSITIVE LOGITS
    声ä¸Ń
    0.08
    ophil
    0.08
     metals
    0.08
     Orth
    0.08
    æĿĤ
    0.07
    ilik
    0.07
    æij©
    0.07
    ount
    0.07
    exceptions
    0.07
     secu
    0.07
    Activations Density 0.009%

    No Known Activations