© 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. 24932
    Prev
    Next
    INDEX
    Explanations

    legal provisions, statutory or code sections

    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
    _claim
    -0.07
    æ²¾æŁĵ
    -0.07
    èĬ¯
    -0.07
    minos
    -0.07
    è¾¾åħĭ
    -0.06
    å¿Į
    -0.06
    éĺµéĺµ
    -0.06
    ä¸įä¼ļ被
    -0.06
    声称
    -0.06
    交æıĽ
    -0.06
    POSITIVE LOGITS
     provisions
    0.10
    æĺİç¡®è§Ħå®ļ
    0.09
    修订
    0.09
    è§Ħå®ļäºĨ
    0.09
    ä¸ĵéŨ
    0.09
    éĢĤçĶ¨èĮĥåĽ´
    0.09
    æĿ¡æĸĩ
    0.09
    æĸ½è¡Į
    0.09
    ä¸ĵéŨçļĦ
    0.09
    å®ĮåĸĦçļĦ
    0.09
    Activations Density 0.029%

    No Known Activations