© 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. 49872
    Prev
    Next
    INDEX
    Explanations

    constant values or configurations

    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
    hie
    -0.07
    循åºı
    -0.07
    _aliases
    -0.07
    à¸Ħรà¸ļ
    -0.07
    æ²¥
    -0.07
    ç§ģèIJ¥
    -0.07
    ä¸į容
    -0.07
    formed
    -0.07
    èĤ¾çĤİ
    -0.07
    ä¹ŁæĽ´
    -0.07
    POSITIVE LOGITS
    /static
    0.09
    (Constant
    0.07
    equip
    0.07
    (Const
    0.07
     hằng
    0.07
     Konst
    0.07
    .Flat
    0.07
    æĪĸå°ı
    0.07
    constant
    0.07
     Const
    0.07
    Activations Density 0.007%

    No Known Activations