© 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. 10479
    Prev
    Next
    INDEX
    Explanations

    specific programming types and symbols

    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
    ervice
    -0.08
    hip
    -0.07
    æĮij
    -0.07
     fleste
    -0.07
    ANCE
    -0.07
    anceled
    -0.07
    creen
    -0.07
    лож
    -0.07
    aga
    -0.07
    ystem
    -0.07
    POSITIVE LOGITS
    sWith
    0.18
    们çļĦ
    0.16
    åĢij
    0.15
    ä»¬åľ¨
    0.15
    (s
    0.15
    们éĥ½
    0.15
    [s
    0.14
    们对
    0.13
    åĢijçļĦ
    0.13
    swith
    0.13
    Activations Density 1.840%

    No Known Activations