© 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. 65093
    Prev
    Next
    INDEX
    Explanations

    mechanical properties

    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
    çħ§èĢĢ
    -0.08
    izen
    -0.07
    waan
    -0.07
    æī¬éķ¿
    -0.07
    ç½®ä¹ĭ
    -0.07
    à¸Ńม
    -0.07
    ÑģкÑĢÑĭ
    -0.07
    ungsweise
    -0.07
    åĴĮåİ¿
    -0.07
    çĮİ人
    -0.07
    POSITIVE LOGITS
    /she
    0.08
    æ¨ĭ
    0.08
     mechanic
    0.08
    æľºæ¢°
    0.08
    kke
    0.07
    physical
    0.07
    éĤ¦
    0.07
    çī©çIJĨ
    0.07
    åĬĽçļĦ
    0.07
    åĬĽåĴĮ
    0.07
    Activations Density 0.389%

    No Known Activations