© 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. 43766
    Prev
    Next
    INDEX
    Explanations

    открыть порты

    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
    ä¸įæĸŃçļĦ
    -0.09
    izing
    -0.09
    izes
    -0.08
    ating
    -0.08
    ing
    -0.08
    ä¸Ģç§į
    -0.08
    åĽŀæĿ¥äºĨ
    -0.07
    ãģĵãģ¨ãģĮå¤ļãģĦ
    -0.07
    ales
    -0.07
    oton
    -0.07
    POSITIVE LOGITS
     volna
    0.10
    wszy
    0.10
    ÑĪиÑģÑĮ
    0.09
     вдÑĢÑĥг
    0.09
    еÑģÑĮ
    0.09
    bsites
    0.09
    вÑĪиÑģÑĮ
    0.08
    URATION
    0.08
    /change
    0.08
    è¶³å¤ŁçļĦ
    0.08
    Activations Density 0.059%

    No Known Activations