© 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. 56281
    Prev
    Next
    INDEX
    Explanations

    unbiased estimator

    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
    alom
    -0.08
    龸çİĭ
    -0.08
    ycl
    -0.07
    à¸Ķิ
    -0.07
     rabat
    -0.07
    auled
    -0.07
     Verg
    -0.07
    nants
    -0.07
     ÒĽÐ¾
    -0.07
    alf
    -0.07
    POSITIVE LOGITS
     unbiased
    0.10
     estim
    0.10
     estimator
    0.09
    误差
    0.08
    æł¡æŃ£
    0.08
    估计
    0.07
     mong
    0.07
    轻信
    0.07
     bias
    0.07
     errors
    0.07
    Activations Density 0.005%

    No Known Activations