© 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. 30830
    Prev
    Next
    INDEX
    Explanations

    by + gerund verb

    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
    为äºĨä¸į
    -0.08
    为äºĨä¿ĿæĬ¤
    -0.08
    à¹Ģà¸ŀืà¹Īà¸Ńà¸Ķ
    -0.07
    为äºĨ
    -0.07
    orest
    -0.07
    ä¸į太
    -0.07
    çĶ±äºİ
    -0.07
    为äºĨæıIJé«ĺ
    -0.07
    aar
    -0.06
     vibes
    -0.06
    POSITIVE LOGITS
    лÑĮкÑĥ
    0.07
    opan
    0.07
    ç»ĻäºĨæĪij
    0.07
    ç»Ļå®ĥ
    0.07
    ng
    0.07
    æıIJä¾ĽäºĨä¸Ģ个
    0.06
    æĺİæĺİæĺ¯
    0.06
    idu
    0.06
     pyt
    0.06
    által
    0.06
    Activations Density 0.076%

    No Known Activations