© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    phylogenetic groups or relatives

    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
    urd
    -0.08
    ä¸įè¦ģå¿ĺè®°
    -0.07
     during
    -0.06
    اسب
    -0.06
    æĮ¥
    -0.06
    imb
    -0.06
    æģ°åĪ°
    -0.06
     conc
    -0.06
    ç¾Ĭ
    -0.06
    _scal
    -0.06
    POSITIVE LOGITS
    缮åīįå·²
    0.09
    éī´å®ļ
    0.09
    éijijå®ļ
    0.09
    éī´å®ļçļĦ
    0.09
     mainland
    0.08
    稳å®ļåĴĮ
    0.08
    FRING
    0.08
    opolitan
    0.08
     genom
    0.08
     subgroup
    0.08
    Activations Density 0.563%

    No Known Activations