© 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. 8092
    Prev
    Next
    INDEX
    Explanations

    if and only if

    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
    _INITIALIZER
    -0.09
    ä¹ĭæīĢ以
    -0.08
    itage
    -0.08
    //*
    -0.08
     myself
    -0.08
    ory
    -0.08
    argas
    -0.08
    ä¼
    -0.08
    fade
    -0.08
    èĻ½å°ı
    -0.08
    POSITIVE LOGITS
    ãģ¨è¨Ģãģ£ãģ¦
    0.09
    ãģ¨ãģĦãģ£ãģ¦
    0.08
     اÛĮÙĨÚ©Ùĩ
    0.07
    ently
    0.07
    ä¹İ
    0.06
    å¾Ĺä¸Ĭ
    0.06
    пи
    0.06
     versa
    0.06
    Âł
    0.06
    è¿Ļ个社ä¼ļ
    0.06
    Activations Density 0.006%

    No Known Activations