© 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. 15662
    Prev
    Next
    INDEX
    Explanations

    passing parameters or arguments

    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
    .desktop
    -0.08
    onsin
    -0.07
    èIJ½ãģ¨ãģĹ
    -0.07
     hò
    -0.07
    æ²Ļé¾Ļ
    -0.07
    apati
    -0.07
    ç¦Ħ
    -0.07
    uur
    -0.07
    ÑĪеÑĤ
    -0.07
    ש×ķ
    -0.07
    POSITIVE LOGITS
    åıĤæķ°
    0.12
    ä¼łåħ¥
    0.11
     parameter
    0.11
     argument
    0.09
     passed
    0.09
     arguments
    0.09
     parameters
    0.09
    åıĤæķ°çļĦ
    0.09
    parameter
    0.08
     Parameter
    0.08
    Activations Density 0.408%

    No Known Activations