© 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. 19508
    Prev
    Next
    INDEX
    Explanations

    android layout attributes

    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
    iau
    -0.07
    ä¼ĺ
    -0.06
     fian
    -0.06
    olit
    -0.06
    indre
    -0.06
    åħīæĺİçļĦ
    -0.06
     Seah
    -0.06
     ÑĢаÑģÑħод
    -0.06
    /met
    -0.06
    -0.06
    POSITIVE LOGITS
    inov
    0.08
    reiro
    0.07
    aders
    0.07
    fle
    0.07
    اÙĩد
    0.07
    ilta
    0.07
    Serve
    0.07
    åĽŃè·¯
    0.07
    lieder
    0.07
    eds
    0.07
    Activations Density 0.001%

    No Known Activations