© 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. 49734
    Prev
    Next
    INDEX
    Explanations

    word followed by closing bracket ]

    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
    rus
    -0.07
    xcd
    -0.07
    ä¸įå¼Ģ
    -0.07
    大年
    -0.07
    -Cs
    -0.07
     напо
    -0.07
    hme
    -0.07
    ero
    -0.07
    anj
    -0.07
    º
    -0.06
    POSITIVE LOGITS
    çĽĪ
    0.08
     Viale
    0.07
    æĮ¡æĿ¿
    0.07
    ponsor
    0.07
    éĢļ天
    0.06
    ×ķ×Ŀ
    0.06
    prav
    0.06
    è¿Ŀåıįä¸Ĭè¿°
    0.06
    ennis
    0.06
    .priv
    0.06
    Activations Density 0.079%

    No Known Activations