© 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. 45742
    Prev
    Next
    INDEX
    Explanations

    defining parameters or process variables

    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
    leder
    -0.08
    _mime
    -0.07
    uhi
    -0.07
    è¿Ļç§įæĥħåĨµ
    -0.07
    nies
    -0.07
    æ³
    -0.07
    à¸Ŀ
    -0.07
    akor
    -0.07
    TypeInfo
    -0.07
    bery
    -0.07
    POSITIVE LOGITS
    åıĤæķ°
    0.14
     parameters
    0.14
     parameter
    0.13
    åıĤæķ°çļĦ
    0.12
    åıĺéĩı
    0.12
     variables
    0.12
     Parameters
    0.12
     Parameter
    0.12
    Parameters
    0.11
    Parameter
    0.11
    Activations Density 0.082%

    No Known Activations