© 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. 19324
    Prev
    Next
    INDEX
    Explanations

    centrifugal

    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
    stown
    -0.09
    iances
    -0.08
    主çļĦ
    -0.08
    itionally
    -0.07
     ingle
    -0.07
    chers
    -0.07
     limpe
    -0.07
    erland
    -0.07
    ìĿį
    -0.07
    lden
    -0.07
    POSITIVE LOGITS
    ugal
    0.11
    yota
    0.09
    idium
    0.08
    uate
    0.08
    éģĵéķ¿
    0.08
    uous
    0.08
    ÙĤد
    0.07
    oid
    0.07
    oxide
    0.07
    èvre
    0.07
    Activations Density 0.011%

    No Known Activations