© 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. 10569
    Prev
    Next
    INDEX
    Explanations

    abstract and mathematical 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
     not
    -0.07
    æŃ£åĢ¼
    -0.07
     only
    -0.07
    ste
    -0.06
    ocom
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    éĥ½æľīäºĨ
    -0.06
    ä¸įåĪ°çļĦ
    -0.06
    ä¸įèµ°
    -0.06
    åľºä¸Ĭ
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.08
    añ
    0.08
     otherwise
    0.07
    绾ç»İ
    0.07
    å¸ĥ鼷
    0.07
    иÑģка
    0.07
    aturan
    0.07
    .gca
    0.07
    æŶæīĢ
    0.07
    alist
    0.07
    Activations Density 0.282%

    No Known Activations