© 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. 61580
    Prev
    Next
    INDEX
    Explanations

    prime factors or divisibility

    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
    iteur
    -0.08
    ØŃاء
    -0.08
    atoire
    -0.08
     ÙħÙĪا
    -0.08
    æ¹ĥ
    -0.07
    åĢ¦æĢł
    -0.07
    rov
    -0.07
    ropp
    -0.07
    gings
    -0.07
    æĨĶ
    -0.07
    POSITIVE LOGITS
    ç»ĵå°¾
    0.08
    oudre
    0.08
    æľ«
    0.07
    ival
    0.07
    è±ļ
    0.07
    yal
    0.07
    ç»ĵè¯Ń
    0.07
    лÑıÑĢ
    0.06
    ä¸ī大
    0.06
    omin
    0.06
    Activations Density 0.002%

    No Known Activations