© 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. 16567
    Prev
    Next
    INDEX
    Explanations

    math roman font math notation

    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
    ation
    -0.10
    ingly
    -0.09
    ions
    -0.08
    樣çļĦ
    -0.08
    ction
    -0.08
    ier
    -0.07
    ÑģÑı
    -0.07
    amiento
    -0.07
    getattr
    -0.07
    ằm
    -0.06
    POSITIVE LOGITS
    ergestellt
    0.12
    à¹Į
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.10
    elÅij
    0.09
    bbe
    0.09
    ãģ¹ãģį
    0.09
    ãģĭãģı
    0.09
    Marshal
    0.08
    cule
    0.08
    teenth
    0.08
    Activations Density 0.015%

    No Known Activations