© 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. 1701
    Prev
    Next
    INDEX
    Explanations

    suffixes like ification, ing, ment

    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
    åıijå±ķä¸Ń
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    en
    -0.06
    欢è¿İæĤ¨
    -0.06
    æĤ¨å½ĵåīį
    -0.06
    建议书
    -0.06
    emeen
    -0.06
    ìĸ´ë¡ľ
    -0.06
    λη
    -0.06
    æľ¬çº§
    -0.05
    POSITIVE LOGITS
    gak
    0.07
    ãģįãĤĥ
    0.07
    iar
    0.07
    ÑĢам
    0.07
    æīĵéĢļ
    0.07
    cé
    0.06
    zeg
    0.06
    uvé
    0.06
    álu
    0.06
    ÃģL
    0.06
    Activations Density 0.699%

    No Known Activations