© 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. 61222
    Prev
    Next
    INDEX
    Explanations

    squaring operations

    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
    ernet
    -0.08
    aku
    -0.07
    ivo
    -0.07
    ise
    -0.07
    ake
    -0.07
    ç³»ç»Łä¸ŃçļĦ
    -0.07
    人æĦı
    -0.07
    è¾īæĺł
    -0.06
    çľĭåľ¨
    -0.06
    ç³»ç»Łæĺ¯
    -0.06
    POSITIVE LOGITS
     squared
    0.12
    Squared
    0.11
    _squared
    0.09
    å¹³æĸ¹
    0.09
    quared
    0.09
    ²
    0.08
    ()?.
    0.08
    ×¢×ķת
    0.08
    .square
    0.08
    ffel
    0.07
    Activations Density 0.033%

    No Known Activations