© 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. 18099
    Prev
    Next
    INDEX
    Explanations

    physics particles like J/psi, eta, lambda

    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
    sha
    -0.08
     гÑĢани
    -0.07
    绣ä¸ĢåĪ°
    -0.07
    éĥ½æĬĬ
    -0.07
     character
    -0.07
    menes
    -0.07
    产åĵģåı¬åĽŀ
    -0.06
    áĥ¬
    -0.06
    ukat
    -0.06
    ILT
    -0.06
    POSITIVE LOGITS
    çļĦç»ĦåIJĪ
    0.09
    ç»ĦåIJĪ
    0.08
     pairs
    0.08
     pair
    0.08
    angk
    0.08
    pairs
    0.07
    composed
    0.07
     Yug
    0.07
    etos
    0.07
    èĬ®
    0.07
    Activations Density 0.015%

    No Known Activations