© 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. 57611
    Prev
    Next
    INDEX
    Explanations

    rounding decimal places

    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
    alus
    -0.07
    ä¸įåİĮ
    -0.07
    åĪ©çļĦ
    -0.07
    éĨIJ
    -0.07
    ä¹Łåıªæĺ¯
    -0.06
    åĸ
    -0.06
    oyer
    -0.06
    çİ°åľ¨å¼Ģå§ĭ
    -0.06
    ailer
    -0.06
     loophole
    -0.06
    POSITIVE LOGITS
    ç°¡
    0.08
    ç®Ģ
    0.07
    round
    0.07
    rox
    0.07
     thủ
    0.07
    (round
    0.07
     Rounds
    0.07
    rok
    0.07
    ment
    0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.07
    Activations Density 0.012%

    No Known Activations