© 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. 4196
    Prev
    Next
    INDEX
    Explanations

    math equations and symbols

    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
    endregion
    -0.07
    URI
    -0.07
    Uri
    -0.07
    erot
    -0.06
    ipt
    -0.06
    ro
    -0.06
    omo
    -0.06
     gá»ĵm
    -0.06
    订ç«ĭ
    -0.06
     Vat
    -0.06
    POSITIVE LOGITS
     rtl
    0.08
    Ø°Ùģ
    0.08
    yclic
    0.07
    _engine
    0.07
    elar
    0.07
    erties
    0.07
    丽èİİ
    0.07
    ä»»éĩį
    0.07
    ilu
    0.07
    çĿ¡ä¸įçĿĢ
    0.07
    Activations Density 0.001%

    No Known Activations