© 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. 2758
    Prev
    Next
    INDEX
    Explanations

    possessives and abbreviations

    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
    imana
    -0.09
    Ñĥго
    -0.07
    istiche
    -0.07
    ation
    -0.07
    ì§ģ
    -0.07
    ToLocal
    -0.07
    /close
    -0.07
    {//
    -0.07
    inux
    -0.07
    ä¾ĽåĽ¾
    -0.07
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.11
    åĬłæĭ¿å¤§
    0.09
    sä
    0.09
    s
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    æĶ¾çŁ¢
    0.08
    俱ä¹IJéĥ¨
    0.07
    æĸ°åĬłåĿ¡
    0.07
    ếm
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    Activations Density 0.063%

    No Known Activations