© 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. 47522
    Prev
    Next
    INDEX
    Explanations

    simulation or simulate

    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
    ening
    -0.09
    ened
    -0.08
    mals
    -0.08
    lessness
    -0.08
    صÙģØ©
    -0.08
    iosk
    -0.07
    iger
    -0.07
    ¿
    -0.07
    messer
    -0.07
    ä¸įé½IJ
    -0.07
    POSITIVE LOGITS
    åĻ¨çļĦ
    0.10
    ilarity
    0.08
    گر
    0.08
    thinkable
    0.08
    Backdrop
    0.07
    acruz
    0.07
    åĻ¨åĴĮ
    0.07
    vast
    0.07
    گرÛĮ
    0.07
    ulators
    0.07
    Activations Density 0.054%

    No Known Activations