© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23215
    Prev
    Next
    INDEX
    Explanations

    site selection

    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
    -speaking
    -0.10
    缸è¾ħ缸æĪIJ
    -0.10
    nya
    -0.08
    ÑģÑı
    -0.08
    IgnoreCase
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    áĢ·
    -0.07
    EDIA
    -0.07
    ÛĮ
    -0.07
    UNET
    -0.07
    POSITIVE LOGITS
    ivity
    0.09
    aylor
    0.08
     AnyObject
    0.08
    باÙĨ
    0.08
    undial
    0.08
    holder
    0.08
    uality
    0.08
    éĻIJãĤĬ
    0.07
    otle
    0.07
    wap
    0.07
    Activations Density 0.056%

    No Known Activations