© 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. 7573
    Prev
    Next
    INDEX
    Explanations

    size measured

    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
    arrêt
    -0.07
    xdb
    -0.07
    æĸ°åŁİ
    -0.07
    ubro
    -0.07
    оваÑĤелÑĮно
    -0.07
    rana
    -0.07
    屿
    -0.06
    achten
    -0.06
     Quantum
    -0.06
    filesize
    -0.06
    POSITIVE LOGITS
    conversion
    0.08
    ä¸Ģå±Ĭ
    0.07
     conversion
    0.07
    vere
    0.07
    oin
    0.07
    eries
    0.07
    æ±ł
    0.07
    å¾·åĪ©
    0.06
     conventions
    0.06
     involved
    0.06
    Activations Density 0.024%

    No Known Activations