© 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. 46340
    Prev
    Next
    INDEX
    Explanations

    group theory and primes

    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
    ÑģÑĤил
    -0.08
    ç¥Ŀç¦ıä½ł
    -0.07
    ijt
    -0.07
    klam
    -0.07
    .authenticate
    -0.07
    çī¹åĮº
    -0.06
    导读
    -0.06
    åĽŀçļĦ
    -0.06
    ä¾£
    -0.06
    Ĵ
    -0.06
    POSITIVE LOGITS
    umber
    0.07
    Ñģме
    0.07
    /modal
    0.07
    æ¿¡
    0.07
    ÃŃz
    0.07
     ÑĤемаÑĤи
    0.07
    WXYZ
    0.07
    ember
    0.07
    ahari
    0.07
    editary
    0.06
    Activations Density 0.004%

    No Known Activations