© 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. 43006
    Prev
    Next
    INDEX
    Explanations

    vanishing points or sets

    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
    åİĭåĢĴ
    -0.08
     budgets
    -0.08
    žd
    -0.08
    enet
    -0.08
    表ä¸Ń
    -0.07
    åIJĦæĸ¹éĿ¢
    -0.07
    ç²Ĺæļ´
    -0.07
    rams
    -0.07
     hÃłi
    -0.07
    budget
    -0.07
    POSITIVE LOGITS
     holes
    0.08
    è¿ŀéĢļ
    0.08
    ekat
    0.07
     radial
    0.07
     cong
    0.07
    holes
    0.07
     rad
    0.07
     hole
    0.07
    URNS
    0.07
    AccessException
    0.06
    Activations Density 0.003%

    No Known Activations