© 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. 42070
    Prev
    Next
    INDEX
    Explanations

    magnetic field description

    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
    sworth
    -0.07
    Interop
    -0.07
    ÑģоÑĢ
    -0.07
    nacht
    -0.07
    ago
    -0.07
    Tweet
    -0.07
     raging
    -0.07
    athom
    -0.07
    ukat
    -0.06
     somehow
    -0.06
    POSITIVE LOGITS
     prelimin
    0.07
     revis
    0.07
    culo
    0.07
    æĥħåĨµåıĬ
    0.07
    åįģåħ«ç«ł
    0.07
    gad
    0.07
    åĪĿæŃ¥
    0.07
    idé
    0.07
    æºIJèĩª
    0.06
     cases
    0.06
    Activations Density 0.161%

    No Known Activations