© 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. 18272
    Prev
    Next
    INDEX
    Explanations

    function, program, script

    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
    vila
    -0.07
    velt
    -0.07
    åĪ°äºĨä¸Ģ个
    -0.06
    æį¢ç®Ĺ
    -0.06
    åĬªåĬĽåĴĮ
    -0.06
    ç²¾ç»ĨåĮĸ管çIJĨ
    -0.06
     Wish
    -0.06
    ç´¯
    -0.06
    มาร
    -0.06
    vera
    -0.06
    POSITIVE LOGITS
    λογ
    0.08
    WithContext
    0.07
    izzati
    0.07
    omanip
    0.07
    .INPUT
    0.07
    imator
    0.07
    æİ¥åįķ
    0.07
    eke
    0.07
    оÑģÑĤÑĮÑİ
    0.07
    estä
    0.07
    Activations Density 0.001%

    No Known Activations