© 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. 49342
    Prev
    Next
    INDEX
    Explanations

    constitute a resolution of the identity

    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
    Ùħز
    -0.08
     Crud
    -0.06
    è®¤çľŁçļĦ
    -0.06
    æ¯ĭ
    -0.06
    alls
    -0.06
    .fast
    -0.06
    ale
    -0.06
    æ·ij
    -0.06
    è£ħ饰设计
    -0.06
    tene
    -0.06
    POSITIVE LOGITS
    à¹īาà¸Ļ
    0.08
    æĦıæĥ³ä¸įåĪ°çļĦ
    0.08
    óln
    0.07
     Mohamm
    0.07
    åĢį
    0.07
    人æĦı
    0.07
    åĴĮæݨ广
    0.07
    gaan
    0.07
     desired
    0.07
    buah
    0.07
    Activations Density 0.020%

    No Known Activations