© 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. 41550
    Prev
    Next
    INDEX
    Explanations

    starting/first position

    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
    strand
    -0.08
     -:
    -0.07
    amp
    -0.07
     yourselves
    -0.07
    gres
    -0.07
    icular
    -0.07
    idis
    -0.07
    ffi
    -0.07
    ç²¾ç¥ŀçĹħ
    -0.07
    icolo
    -0.07
    POSITIVE LOGITS
    parsers
    0.07
     à¸Ħู
    0.07
    åIJĦ
    0.07
    æ°¸åĴĮ
    0.07
    æĸ½æīĵ
    0.06
     Hicks
    0.06
     Woody
    0.06
    åIJĦæľī
    0.06
     upt
    0.06
    è´¨çļĦ
    0.06
    Activations Density 0.018%

    No Known Activations