© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    loop initialization with i

    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
    çļĦæī§è¡Į
    -0.07
    valt
    -0.06
     bin
    -0.06
    exe
    -0.06
    ular
    -0.06
    ׼×Ļ
    -0.06
    åĪ°åºķæĺ¯
    -0.06
     grav
    -0.06
    azar
    -0.06
     Doming
    -0.06
    POSITIVE LOGITS
    ÒĽÑĭ
    0.08
    ushman
    0.08
    odus
    0.07
    åĽłæĤ¨çļĦ
    0.07
    _simps
    0.07
    asel
    0.07
    may
    0.07
    äºĭçļĦ
    0.07
    untas
    0.07
    ׾×IJ
    0.07
    Activations Density 0.009%

    No Known Activations