© 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. 13060
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with punctuation

    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
    teman
    -0.10
    ä¸ĢçĤ¹çļĦ
    -0.07
    illes
    -0.07
    eneral
    -0.07
    rlen
    -0.07
    æĮ¡
    -0.07
    年头
    -0.07
    Stand
    -0.07
    è¿ŀè¿ŀ
    -0.07
    odb
    -0.06
    POSITIVE LOGITS
    ÑĥÑĤа
    0.07
    rtype
    0.06
    à¹Īาà¸ĩ
    0.06
     klok
    0.06
    ỳ
    0.06
     Borsa
    0.06
    å¾Īä¸į
    0.06
    (({
    0.06
    hô
    0.06
    pira
    0.06
    Activations Density 0.245%

    No Known Activations