© 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. 20151
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
    éĢIJå¹´
    -0.07
    æ¯ıæĿ¡
    -0.07
    ä¹ĭæīĢ以
    -0.07
    å¿ħ须符åIJĪ
    -0.06
    åħ¬å®³
    -0.06
    çľĭä¸Ģçľ¼
    -0.06
    ä¸Ģæĸ¹
    -0.06
     Ñģез
    -0.06
    ä¸įæĺİ
    -0.06
    oyer
    -0.06
    POSITIVE LOGITS
    åĴĮ第
    0.07
     retribu
    0.07
    å·©åĽº
    0.07
     teht
    0.07
     teach
    0.07
    ód
    0.07
    ç°¿
    0.07
     onwards
    0.07
    midd
    0.07
    starter
    0.07
    Activations Density 0.121%

    No Known Activations