© 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. 58617
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    éĩijé¾Ļ
    -0.07
    ene
    -0.07
    çľĭä½ľ
    -0.07
     introduced
    -0.06
    TRACE
    -0.06
     Giri
    -0.06
    èģ²
    -0.06
    .shortcuts
    -0.06
     Har
    -0.06
     introduction
    -0.06
    POSITIVE LOGITS
    丽èİİ
    0.08
    kob
    0.08
    anded
    0.07
    ITED
    0.07
    ç»ĻæĪijçļĦ
    0.07
    ceb
    0.07
    REFERRED
    0.07
    apy
    0.07
    à²Ĥದ
    0.07
     иÑĤого
    0.07
    Activations Density 0.006%

    No Known Activations