© 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. 28925
    Prev
    Next
    INDEX
    Explanations

    superscript, subscript, fractional parts

    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
     strncmp
    -0.08
    memcmp
    -0.08
     memcmp
    -0.08
    è®¤çľŁç»Ħç»ĩ
    -0.07
    æĸ
    -0.07
    inger
    -0.07
    acor
    -0.07
    aliza
    -0.07
    UMA
    -0.07
    .createObject
    -0.07
    POSITIVE LOGITS
     ÑģнизÑĥ
    0.08
     alt
    0.08
     versehen
    0.07
     div
    0.07
     altına
    0.07
    ALT
    0.07
    .alt
    0.07
     subscript
    0.07
     Ons
    0.07
    ãģ«ãģı
    0.07
    Activations Density 0.030%

    No Known Activations