© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48473
    Prev
    Next
    INDEX
    Explanations

    names from emails

    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
     Kass
    -0.07
     Laut
    -0.07
     solid
    -0.07
    obar
    -0.07
     зе
    -0.07
     ÙĪصÙģ
    -0.06
    åĩĨç¡®åľ°
    -0.06
    Õµ
    -0.06
    à¸Ĺะà¹Ģล
    -0.06
    æııè¿°
    -0.06
    POSITIVE LOGITS
    æ¥ł
    0.08
    idar
    0.07
    .override
    0.07
    CTL
    0.07
     Entw
    0.07
    ilea
    0.07
    çĩ
    0.07
    amate
    0.07
    olv
    0.06
    itel
    0.06
    Activations Density 0.367%

    No Known Activations