© 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. 18220
    Prev
    Next
    INDEX
    Explanations

    geoXml

    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
    etus
    -0.08
    ä»ĸ们已ç»ı
    -0.08
    .onError
    -0.07
    ä¸Ģ身
    -0.07
     fine
    -0.07
    itez
    -0.07
    ëĤŃ
    -0.07
    æĸİ
    -0.07
    æŃ³
    -0.07
    ä¸İåħ±
    -0.07
    POSITIVE LOGITS
    åIJĪçIJĨçļĦ
    0.09
    åIJĪçIJĨ
    0.09
     reasonable
    0.08
    åIJĪçIJĨæĢ§
    0.08
    odob
    0.07
    reasonable
    0.07
    ç§ijåѦåIJĪçIJĨ
    0.07
    ä¸ĢèĪ¬ä¸įä¼ļ
    0.07
    èĢĥèĻijåĪ°
    0.07
    Depending
    0.07
    Activations Density 0.068%

    No Known Activations