© 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. 62283
    Prev
    Next
    INDEX
    Explanations

    initialValue to finalValue, moon orbiting, rows to columns

    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
     Dich
    -0.07
    prise
    -0.07
    usas
    -0.07
     Zas
    -0.07
    åħ¶ä¸º
    -0.07
    دة
    -0.07
    uber
    -0.06
    ura
    -0.06
     dich
    -0.06
    reply
    -0.06
    POSITIVE LOGITS
    æĢ»æ¯Ķ
    0.08
    èĺ¿
    0.08
    åĴĮå°ļ
    0.08
    º
    0.08
    ervi
    0.07
    ä¸įæ¯Ķ
    0.07
    ä¸İ
    0.07
    é¼ł
    0.07
    ç³»ç»Łä¸İ
    0.07
    esel
    0.07
    Activations Density 0.131%

    No Known Activations