© 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. 39959
    Prev
    Next
    INDEX
    Explanations

    patent applications compositions materials

    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
    屿
    -0.07
    geg
    -0.07
    áº
    -0.07
    usst
    -0.07
    ekan
    -0.07
    beit
    -0.07
     Regular
    -0.07
    injau
    -0.07
    äck
    -0.07
    Regular
    -0.07
    POSITIVE LOGITS
     herein
    0.09
     embodiments
    0.08
     invention
    0.08
     Patent
    0.08
     Applicant
    0.08
    å®ŀæĸ½ä¾ĭ
    0.08
    ä¼ĺéĢī
    0.08
     inventive
    0.07
     inventions
    0.07
    æĸ¹æ³ķæĺ¯
    0.07
    Activations Density 1.791%

    No Known Activations