© 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. 57993
    Prev
    Next
    INDEX
    Explanations

    @ sign followed by file or license

    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
    è´¨çļĦ
    -0.08
    quine
    -0.08
    WithValue
    -0.08
    à¸Ĺาà¸ĩà¸ģาร
    -0.08
    veux
    -0.08
     herrer
    -0.08
    leistung
    -0.08
    ëį°ìļĶ
    -0.07
    à§įতà§ģ
    -0.07
    leit
    -0.07
    POSITIVE LOGITS
    SuppressWarnings
    0.11
    ï¸ı
    0.11
    ï¸İ
    0.11
    sWith
    0.10
    staticmethod
    0.09
    à¥įस
    0.09
    einander
    0.08
    fortawesome
    0.08
    ting
    0.08
     slightest
    0.08
    Activations Density 0.145%

    No Known Activations