© 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. 42824
    Prev
    Next
    INDEX
    Explanations

    hurricane events

    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
    Forge
    -0.08
    æ¡£
    -0.08
    å°ıå¿ĥ
    -0.07
    äºİ人
    -0.07
    é¼İ
    -0.07
    agl
    -0.06
    èĤ¤è´¨
    -0.06
    kilde
    -0.06
    é£İåIJ¹
    -0.06
     verb
    -0.06
    POSITIVE LOGITS
    ç§
    0.08
    _allocate
    0.08
    izr
    0.08
    à¹ģà¸Īà¸ģ
    0.08
    ĶĦ
    0.08
     numbered
    0.08
    æĹłéĻIJ
    0.08
    æĹłéĻIJçļĦ
    0.08
    สำรวà¸Ī
    0.07
     indefinitely
    0.07
    Activations Density 0.008%

    No Known Activations