© 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. 28923
    Prev
    Next
    INDEX
    Explanations

    number/index/stars/play

    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
    ìŬ
    -0.07
    çļĦä¸Ģçīĩ
    -0.06
    ously
    -0.06
    вакÑĥ
    -0.06
    ãģ£ãģ¨
    -0.06
    aries
    -0.06
    enuity
    -0.06
     hor
    -0.06
    好åŃ©åŃIJ
    -0.06
    č↵č↵č↵
    -0.06
    POSITIVE LOGITS
    åįijå¾®
    0.07
    庸
    0.07
    agnes
    0.07
    ernet
    0.06
    康
    0.06
    Tho
    0.06
    æľīçĶŁ
    0.06
    ló
    0.06
    éļĭ
    0.06
    .Skin
    0.06
    Activations Density 0.003%

    No Known Activations