© 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. 9259
    Prev
    Next
    INDEX
    Explanations

    ordinal suffix or index

    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
    ä¹ı
    -0.06
    å®ŀåľ¨
    -0.06
    åĴĮæľ¬
    -0.06
     haven
    -0.06
    ä¸įè¾¾
    -0.06
    ŀ
    -0.06
    port
    -0.06
     complimentary
    -0.06
    åĴĮä¸Ģ
    -0.06
    æĽ
    -0.06
    POSITIVE LOGITS
    idane
    0.09
    anness
    0.09
    esome
    0.08
    ullets
    0.08
    津津
    0.08
    ocoder
    0.07
    ullet
    0.07
    ë²Ī째
    0.07
    æĪIJé¾Ļ
    0.07
    à¸Ħัà¸Ļ
    0.07
    Activations Density 0.006%

    No Known Activations