© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39382
    Prev
    Next
    INDEX
    Explanations

    coordinates, size, unit, origin, starts

    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
    éĻ·
    -0.07
    CEPT
    -0.07
    ׾×ij
    -0.07
    ç½®ä¹ĭ
    -0.07
     Ria
    -0.07
     ÑħаÑĢакÑĤеÑĢ
    -0.06
     Personnel
    -0.06
    Į¨
    -0.06
    elow
    -0.06
    æĩ
    -0.06
    POSITIVE LOGITS
    Defined
    0.08
    亲åıĭ
    0.07
    æĺ¯æĿ¥èĩª
    0.07
    defined
    0.07
     defined
    0.07
    ä¸İå®ŀéĻħ
    0.07
    æĺ¯ç»ıè¿ĩ
    0.07
     chosen
    0.07
    Enlarge
    0.07
    éļ¾æ±Ĥ
    0.07
    Activations Density 0.037%

    No Known Activations