© 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. 51322
    Prev
    Next
    INDEX
    Explanations

    geometric series and its application

    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
    _shuffle
    -0.08
    insky
    -0.07
    rist
    -0.07
    eree
    -0.07
    AspectRatio
    -0.07
     Grace
    -0.07
    Grace
    -0.07
    ä»İè½»
    -0.07
    riterion
    -0.07
    _require
    -0.06
    POSITIVE LOGITS
     Generic
    0.09
     Formula
    0.08
     formula
    0.08
    åħ¬å¼ı
    0.08
    计ç®Ĺåħ¬å¼ı
    0.08
     Æ°á»Ľc
    0.08
    _formula
    0.08
     Comput
    0.08
    Formula
    0.08
     formulas
    0.07
    Activations Density 0.012%

    No Known Activations