© 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. 45273
    Prev
    Next
    INDEX
    Explanations

    function, ability, role, fluid, initiation

    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
    çł´å¤©
    -0.09
    åĴĮ缮æłĩ
    -0.08
     exploit
    -0.08
    target
    -0.08
    evo
    -0.07
     recherch
    -0.07
    缮æłĩ
    -0.07
     vandal
    -0.07
     target
    -0.07
    quen
    -0.07
    POSITIVE LOGITS
     regulates
    0.09
     regulated
    0.09
     regulate
    0.09
    è°ĥèĬĤ
    0.08
    æİĮ管
    0.08
    æ»ĭåħ»
    0.08
     regulating
    0.08
    æ»ĭ润
    0.08
    ç»Ĩèħ»
    0.08
    åIJĦåı¸
    0.08
    Activations Density 0.001%

    No Known Activations