© 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. 13130
    Prev
    Next
    INDEX
    Explanations

    infinity, nan, or finite

    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
    å¹´çļĦåİĨåı²
    -0.08
    以æĿ¥
    -0.08
    hip
    -0.08
    á»ģn
    -0.07
    åİĨåı²åĴĮ
    -0.07
     подко
    -0.07
     ********************************************************************************
    -0.07
    .objects
    -0.07
    ä¿¡çļĦ
    -0.07
    anson
    -0.07
    POSITIVE LOGITS
     inf
    0.08
    odom
    0.07
     ден
    0.07
    大åĵŃ
    0.07
    æī±ãģĦ
    0.06
    å¡Ķå°Ķ
    0.06
    пÑĢе
    0.06
    Ĩµ
    0.06
    æĪ·
    0.06
    åĶij
    0.06
    Activations Density 0.003%

    No Known Activations