© 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. 34459
    Prev
    Next
    INDEX
    Explanations

    copyright notices and includes

    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
    odon
    -0.08
    ä¸ŀ
    -0.08
    å¼ķ
    -0.07
    XHR
    -0.07
     yyn
    -0.07
    .Byte
    -0.07
    念
    -0.07
    icola
    -0.07
    zens
    -0.07
    ICO
    -0.07
    POSITIVE LOGITS
    éĢļè¿ĩæŃ¤æ¬¡
    0.08
     validations
    0.07
     Logic
    0.07
     logic
    0.07
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    0.07
    sap
    0.07
     maman
    0.07
    该款
    0.07
    validation
    0.07
    atos
    0.07
    Activations Density 0.956%

    No Known Activations