© 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. 31382
    Prev
    Next
    INDEX
    Explanations

    spectral lines and absorption

    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
    thane
    -0.08
    @c
    -0.07
    ashi
    -0.07
    ç½ijç«Ļåľ°åĽ¾
    -0.07
    çİ©å¾Ĺ
    -0.07
    娩
    -0.07
    xor
    -0.07
     Thames
    -0.07
     ple
    -0.07
    ä¸İ设计
    -0.07
    POSITIVE LOGITS
     spectrum
    0.08
    çªĦ
    0.07
    çĮĿ
    0.07
     Laser
    0.07
    åĹĵ
    0.07
     spectro
    0.07
     unresolved
    0.07
     ÑĥÑĪи
    0.07
    ç¦ģ
    0.07
     spectra
    0.07
    Activations Density 0.003%

    No Known Activations