© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8989
    Prev
    Next
    INDEX
    Explanations

    stretch and stretching

    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
    ãģ¥ãģij
    -0.08
    ะ
    -0.08
    æī§è¡Įèij£äºĭ
    -0.07
    ä¸įæĺİçļĦ
    -0.07
    лоÑĤ
    -0.07
    å·¥ç¨ĭéĻ¢
    -0.07
    itian
    -0.07
    å¾Ģ缴
    -0.07
    åŀĴ
    -0.07
    å®ļäºĨ
    -0.07
    POSITIVE LOGITS
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.09
    ening
    0.09
    /stretch
    0.08
    issage
    0.08
    اÙĪز
    0.08
    伸ãģ°
    0.07
     Maak
    0.07
    ToFit
    0.07
    /ss
    0.07
    ä¸įæĭĶ
    0.07
    Activations Density 0.015%

    No Known Activations