© 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. 12459
    Prev
    Next
    INDEX
    Explanations

    Cyrillic word fragments

    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
    ize
    -0.08
    ÑģовеÑģÑĤ
    -0.06
    дÑĮми
    -0.06
    ish
    -0.06
    cito
    -0.06
    доÑĤо
    -0.06
    ities
    -0.06
     ç§ģ
    -0.06
    ersed
    -0.06
    ç»
    -0.06
    POSITIVE LOGITS
    ÛĮ
    0.10
    nya
    0.09
    Ìģ
    0.09
    aData
    0.09
    ï¸İ
    0.09
    sheets
    0.09
    ê°ĦìĿĺ
    0.08
    大åѦåĩºçīĪ社
    0.08
    ynchronously
    0.08
    çļĦãģ«ãĤĤ
    0.07
    Activations Density 0.028%

    No Known Activations