© 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. 38844
    Prev
    Next
    INDEX
    Explanations

    mathematical/technical terms

    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
    /../
    -0.09
    lus
    -0.08
    onom
    -0.08
    rack
    -0.07
    umph
    -0.07
    bum
    -0.07
    (?)
    -0.07
    äºĮåŃĹ
    -0.06
    æĺŁçº§
    -0.06
    å¾ĢæĹ¥
    -0.06
    POSITIVE LOGITS
     olev
    0.07
    ivre
    0.07
    iaan
    0.07
    ãģ¤ãģĦãģŁ
    0.06
    анÑĤа
    0.06
    /pages
    0.06
    uros
    0.06
    pace
    0.06
    paging
    0.06
    onsel
    0.06
    Activations Density 0.064%

    No Known Activations