© 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. 49093
    Prev
    Next
    INDEX
    Explanations

    statistical analysis

    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
    èĽ¾
    -0.07
    åıį
    -0.07
    åĤ³
    -0.07
     fa
    -0.07
    icont
    -0.06
     fur
    -0.06
    åľ¨ä¸ĸ
    -0.06
    ä¼ł
    -0.06
    _UNDEFINED
    -0.06
     Seam
    -0.06
    POSITIVE LOGITS
    stat
    0.09
    ç»Łè®¡
    0.09
     Stat
    0.09
     Statistik
    0.09
     Statistical
    0.09
    Statistic
    0.09
    Stat
    0.08
    colar
    0.08
     statistic
    0.08
    éļıæľº
    0.08
    Activations Density 0.009%

    No Known Activations