© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16971
    Prev
    Next
    INDEX
    Explanations

    graph matrices and Laplacians

    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
    æĢĢä¸Ń
    -0.08
     unprotected
    -0.07
    èī°
    -0.06
    çĶ
    -0.06
    æĢĢéĩĮ
    -0.06
    æĭĿ
    -0.06
    åĨĴçĿĢ
    -0.06
    åĴ
    -0.06
     ש׾×Ļ
    -0.06
    使å®ĥ
    -0.06
    POSITIVE LOGITS
    为åħ¨åĽ½
    0.08
    æĿİå®Ĺ
    0.08
    ipp
    0.08
    ipu
    0.07
    INGTON
    0.07
    anggal
    0.07
    秩
    0.07
     pij
    0.07
     isConnected
    0.07
     triang
    0.07
    Activations Density 0.013%

    No Known Activations