© 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. 15335
    Prev
    Next
    INDEX
    Explanations

    shape memory alloys

    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
    ç½²
    -0.09
    丰
    -0.07
    æŀ¶è®¾
    -0.07
    款
    -0.07
    设æĸ½
    -0.06
    设æĸ½çļĦ
    -0.06
    èĴ¸èĴ¸æĹ¥ä¸Ĭ
    -0.06
    ç½Ħ
    -0.06
     multiples
    -0.06
    å¤ļæĸ¹
    -0.06
    POSITIVE LOGITS
    uhu
    0.09
    ÑĢоди
    0.08
    lite
    0.08
    VERR
    0.08
    ĥĿ
    0.08
    à¸ģรรม
    0.08
    à¸Ĺัà¸Ļ
    0.08
    orra
    0.08
    quir
    0.08
    allis
    0.08
    Activations Density 0.003%

    No Known Activations