© 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. 50917
    Prev
    Next
    INDEX
    Explanations

    question description

    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
    å¿ħè¦ģ
    -0.09
    áīµ
    -0.08
    =yes
    -0.07
    uzzi
    -0.07
    å¿ħè¦ģçļĦ
    -0.07
    åĿļ强
    -0.07
    çļĦåIJĦç§į
    -0.07
    اة
    -0.07
    该æľīçļĦ
    -0.07
    ugno
    -0.07
    POSITIVE LOGITS
     about
    0.08
     to
    0.07
    äºİè¡Į
    0.07
    ffin
    0.07
    缮çŀª
    0.07
    åľ¨äºİ
    0.07
     for
    0.07
    oris
    0.07
     bahwa
    0.07
     tentang
    0.07
    Activations Density 0.048%

    No Known Activations