© 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. 7804
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and scientific notation

    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
    åĪ°æŶ
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
     Nato
    -0.06
    bbc
    -0.06
     пÑĢово
    -0.06
     HACK
    -0.06
    ·
    -0.06
    Scenario
    -0.06
    egg
    -0.06
    ä»Ģä¹Īä¸ľè¥¿
    -0.06
    POSITIVE LOGITS
    legate
    0.07
     Beno
    0.07
    æĭİ
    0.07
    TargetException
    0.07
    où
    0.07
    azah
    0.07
    eus
    0.07
    peat
    0.07
    ä¸ĢæĦı
    0.07
    ä»ĸ羣çļĦ
    0.07
    Activations Density 0.061%

    No Known Activations