© 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. 38364
    Prev
    Next
    INDEX
    Explanations

    average statistics quant templates

    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
    oyer
    -0.07
    çŁ¥ä¹ĭ
    -0.07
     ([[
    -0.07
    çŁ¥åħ¶
    -0.07
     //<
    -0.07
     quá»·
    -0.07
    åį³çĶ¨
    -0.06
    aly
    -0.06
    BM
    -0.06
    ç±»ä¸ĵä¸ļ
    -0.06
    POSITIVE LOGITS
    ÙĨد
    0.07
    tal
    0.07
    对æķ´ä¸ª
    0.07
    丹çĶ°
    0.07
    izon
    0.07
    人æīį
    0.07
    quat
    0.07
    ÑĢ
    0.07
    ourd
    0.07
    åģĩ
    0.07
    Activations Density 0.100%

    No Known Activations