© 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. 26513
    Prev
    Next
    INDEX
    Explanations

    intensity and amplitude

    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
    _AG
    -0.08
    æµģåĬ¨æĢ§
    -0.08
    หาร
    -0.07
    éĺ»éļĶ
    -0.07
    _definitions
    -0.07
    Ñĸм
    -0.07
    ÙĪÙħÛĮ
    -0.07
    interop
    -0.07
    zien
    -0.07
    cec
    -0.07
    POSITIVE LOGITS
    Intensity
    0.10
     intensity
    0.09
    强度
    0.08
    强度çļĦ
    0.07
    _intensity
    0.07
    itta
    0.07
    è¶Ĭ强
    0.07
    åģļ强
    0.07
    èĭ¥å¹²æĦıè§ģ
    0.07
    Quantity
    0.07
    Activations Density 0.014%

    No Known Activations