© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60121
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    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
    lot
    -0.06
    èIJ½äºİ
    -0.06
    ors
    -0.06
    çĹ¹
    -0.06
    åĪ°
    -0.06
    èĢ½æIJģ
    -0.06
    ÃŃ
    -0.06
    icity
    -0.05
    ierre
    -0.05
    ver
    -0.05
    POSITIVE LOGITS
    ationToken
    0.08
    æѦç¥ŀ
    0.08
    วà¸ĩ
    0.08
    çİ°ä½ı
    0.08
     Ende
    0.07
    gai
    0.07
     paramName
    0.07
    (para
    0.07
    أة
    0.07
    formats
    0.07
    Activations Density 0.008%

    No Known Activations