© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    elements and chemical compounds

    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
    æ¯ıæĿ¡
    -0.09
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    æ¯ıä¸ĢæĿ¡
    -0.08
    .setLevel
    -0.08
    æ¯ıåĪ°
    -0.08
    æĺ¯çľŁçļĦ
    -0.08
    oplevel
    -0.08
    kent
    -0.08
    ISTI
    -0.08
    _subtype
    -0.08
    POSITIVE LOGITS
     atoms
    0.07
    ç»ĦæĪIJ
    0.07
    ç»ĦæĪIJçļĦ
    0.07
    pren
    0.07
    æ°§
    0.07
     allein
    0.06
    á»ī
    0.06
    çĽ¾
    0.06
     noble
    0.06
     outnumber
    0.06
    Activations Density 0.003%

    No Known Activations