© 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. 15655
    Prev
    Next
    INDEX
    Explanations

    bool, string, odd, Alternating, Bird

    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
    argin
    -0.08
    éĹ»è¨Ģ
    -0.07
    åIJĦ项活åĬ¨
    -0.07
    dea
    -0.07
     hyper
    -0.07
    æĽ´åĬłæĸ¹ä¾¿
    -0.07
    该éĻ¢
    -0.07
     Tol
    -0.06
    ello
    -0.06
    ARGE
    -0.06
    POSITIVE LOGITS
     inilah
    0.08
    åİĭåĢĴ
    0.07
    ç»´äºļ
    0.07
    åĬłä¸Ĭ
    0.07
    å°Ķåħĭ
    0.07
    evos
    0.07
    产åīį
    0.07
    azed
    0.07
    ÑĥÑĤа
    0.07
    ecca
    0.07
    Activations Density 0.006%

    No Known Activations