© 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. 62554
    Prev
    Next
    INDEX
    Explanations

    chemical compound suffixes

    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
    annes
    -0.08
    åķ¡
    -0.07
    举
    -0.07
    èĦļä¸ĭçļĦ
    -0.07
    aldi
    -0.07
    ville
    -0.07
    æ¡¥éķĩ
    -0.07
    utte
    -0.07
    unt
    -0.07
    jan
    -0.06
    POSITIVE LOGITS
     dissoci
    0.08
    åľ¨æ°´ä¸Ń
    0.08
    ilha
    0.08
     dissolution
    0.08
    åľ¨æ°´éĩĮ
    0.07
     diss
    0.07
     dissolved
    0.07
     Diss
    0.07
    ä¸ī线
    0.07
    çµ®
    0.07
    Activations Density 0.010%

    No Known Activations