© 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. 57551
    Prev
    Next
    INDEX
    Explanations

    calibration drift and correction

    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
    ç§ijåѦçłĶ究éĻ¢
    -0.08
     banh
    -0.07
    ãģİãĤĬ
    -0.07
    æĭŁ
    -0.07
    ç²¹
    -0.07
    éħİ
    -0.07
    heb
    -0.07
     itib
    -0.07
    ocop
    -0.07
    Scores
    -0.07
    POSITIVE LOGITS
     calibration
    0.10
     uneven
    0.09
     Calibration
    0.08
    åľ¨æł¡
    0.08
    æł¡
    0.08
    ä¸įåĿĩ
    0.08
     calibrated
    0.08
    æł¡åĩĨ
    0.08
     unbek
    0.08
    æł¡æŃ£
    0.08
    Activations Density 0.078%

    No Known Activations