© 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. 56736
    Prev
    Next
    INDEX
    Explanations

    sum over i, j

    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
     Charlottesville
    -0.08
    /ns
    -0.07
     Isab
    -0.07
    Ĥ¬
    -0.07
    人ä½ĵåĨħ
    -0.07
    ayu
    -0.07
    åIJĦåĽ½çļĦ
    -0.07
    aldas
    -0.07
    è¿Ļ两ä½į
    -0.07
    edula
    -0.07
    POSITIVE LOGITS
     weaker
    0.07
    eller
    0.07
    otos
    0.07
    æĺķ
    0.06
    bacher
    0.06
    letcher
    0.06
    ä¼ijæģ¯
    0.06
     darker
    0.06
     lit
    0.06
    çķĮ
    0.06
    Activations Density 0.005%

    No Known Activations