© 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. 8067
    Prev
    Next
    INDEX
    Explanations

    size, weight, molecular mass, dispersion

    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
    ehrt
    -0.08
    ç£ģåĬĽ
    -0.07
    _shared
    -0.07
    çĪ±åĽ½ä¸»ä¹ī
    -0.07
    ehren
    -0.07
     volta
    -0.07
     shared
    -0.07
    udin
    -0.07
     Ñģоз
    -0.07
    ToDevice
    -0.07
    POSITIVE LOGITS
    æİĴåºı
    0.07
    åIJĵ人
    0.07
    ispers
    0.07
    itaire
    0.07
    Sizer
    0.07
    -sort
    0.07
    atoon
    0.07
     ÑĦÑĢак
    0.07
    äºĮ段
    0.07
     dispers
    0.06
    Activations Density 0.015%

    No Known Activations