© 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. 61140
    Prev
    Next
    INDEX
    Explanations

    calculus integrals and limits

    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
    æµĭè¯ķç»ĵæŀľ
    -0.08
     ÑĤÑĢе
    -0.08
    ieve
    -0.07
    abia
    -0.07
     moduleId
    -0.07
     bytearray
    -0.07
    è´´èĨľ
    -0.07
    onti
    -0.07
     Modules
    -0.07
    æ±°
    -0.07
    POSITIVE LOGITS
    ä»°
    0.08
     rectangular
    0.08
    çīĩçļĦ
    0.08
    çļĦåĮºåŁŁ
    0.08
     Boundary
    0.08
    ayload
    0.08
    å°
    0.07
    olumes
    0.07
    åĮºåŁŁåĨħ
    0.07
    .Rect
    0.07
    Activations Density 0.020%

    No Known Activations