© 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. 62265
    Prev
    Next
    INDEX
    Explanations

    XML/XIB/Storyboard attributes

    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
    åľ¨è®¾è®¡
    -0.07
    ¬ģ
    -0.07
    orea
    -0.07
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    rody
    -0.07
    olle
    -0.07
    æĺ¯ä¸Ģå¹´
    -0.07
    Ñĸб
    -0.07
    eil
    -0.07
    оÑĢо
    -0.07
    POSITIVE LOGITS
    atic
    0.07
    æĭĨ
    0.07
    hots
    0.07
    ![
    0.06
    ave
    0.06
    ers
    0.06
    éij«
    0.06
    istration
    0.06
    æ¸Ĭ
    0.06
    å´©
    0.06
    Activations Density 0.087%

    No Known Activations