© 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. 34146
    Prev
    Next
    INDEX
    Explanations

    prime numbers

    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
    orsa
    -0.10
    batim
    -0.09
    اظ
    -0.08
    ilda
    -0.08
    Ùijع
    -0.08
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    -0.08
     Mois
    -0.08
    VAS
    -0.08
    第ä¸Ģ人æ°ijåĮ»éĻ¢
    -0.08
    .Abs
    -0.08
    POSITIVE LOGITS
    åĪĹ表
    0.08
    åİĨåı²ä¸Ĭ
    0.07
     primes
    0.07
    ä¸ĭä¸Ģ个
    0.07
     list
    0.07
     prime
    0.06
     candidate
    0.06
     Candidate
    0.06
    åĪĹ表ä¸Ń
    0.06
    List
    0.06
    Activations Density 0.017%

    No Known Activations