© 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. 29560
    Prev
    Next
    INDEX
    Explanations

    Tao, Doyle, discourse, oom

    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
    tings
    -0.10
    缸è¾ħ缸æĪIJ
    -0.10
    äºĭåįĬåĬŁåĢį
    -0.10
    ðu
    -0.09
    uations
    -0.09
    Ñīиков
    -0.09
    Ñīик
    -0.09
    Ñīиками
    -0.09
    Ñīика
    -0.09
    Ñīики
    -0.09
    POSITIVE LOGITS
    erness
    0.09
    Ùĭ
    0.09
    æł¼æĭīæĸ¯
    0.08
    erweise
    0.08
    edly
    0.07
    aic
    0.07
    alog
    0.07
    ä¸ĬçļĦ
    0.07
    ä¸įæĺİçļĦ
    0.07
    à¹Į
    0.07
    Activations Density 0.004%

    No Known Activations