© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
    åĪĨåĪ«ä¸İ
    -0.07
    äºĮçļĦ
    -0.06
    herited
    -0.06
    Ø´ÙĨ
    -0.06
    æ¡¥éķĩ
    -0.06
    åħ¶ä¸İ
    -0.06
    ç«ĭ马
    -0.06
    è¦ģä¹Ī
    -0.06
    /apt
    -0.06
    .flip
    -0.06
    POSITIVE LOGITS
    æħ
    0.07
    avier
    0.07
    interop
    0.07
    пÑĥлÑĮ
    0.07
    GEST
    0.07
     Parkway
    0.07
    uche
    0.07
    aven
    0.07
    å¢
    0.07
    èį¨
    0.07
    Activations Density 0.006%

    No Known Activations