© 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. 25263
    Prev
    Next
    INDEX
    Explanations

    matters or difference

    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
     myself
    -0.09
    orse
    -0.08
     Yourself
    -0.08
    uelos
    -0.08
     himself
    -0.08
    edImage
    -0.08
    adeiras
    -0.08
    ältä
    -0.08
    æľīæīĢæĢĿ
    -0.08
    æĪijçļĦä¼ģä¸ļ
    -0.08
    POSITIVE LOGITS
    fully
    0.08
    à¹ĥà¸Ļà¸ģาร
    0.07
     whether
    0.07
     deciding
    0.07
     when
    0.07
    æĪIJè´¥
    0.07
     banget
    0.07
     determining
    0.07
    ful
    0.07
    äºİå¿ĥ
    0.07
    Activations Density 0.087%

    No Known Activations