© 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. 62434
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or legal terms

    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
    åľ¨åŃ¦ä¹łä¸Ń
    -0.08
    éĤģ
    -0.07
    çŀ©
    -0.07
    大计
    -0.07
    xffff
    -0.07
    yf
    -0.07
    ×ķרת
    -0.07
    åĢª
    -0.06
    ampi
    -0.06
    ylum
    -0.06
    POSITIVE LOGITS
    eros
    0.07
    anned
    0.06
    ereo
    0.06
     Primary
    0.06
    erti
    0.06
    è°ĥæŁ¥åıijçİ°
    0.06
    ensburg
    0.06
    enen
    0.06
    æĺ¨å¤ľ
    0.06
    äºŃ
    0.06
    Activations Density 0.003%

    No Known Activations