© 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. 13444
    Prev
    Next
    INDEX
    Explanations

    code development

    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
     Spl
    -0.07
    spl
    -0.07
    èİ·æĤī
    -0.07
    betes
    -0.07
    è°ĵä¹ĭ
    -0.07
     Clos
    -0.07
     sogenannte
    -0.06
    æs
    -0.06
    ä¸įè¿Ľ
    -0.06
    ç«ĭ项
    -0.06
    POSITIVE LOGITS
    igg
    0.07
    åīįåħĪ
    0.07
    csr
    0.07
    åĢ¾åIJij
    0.07
     sobres
    0.07
    丽èİİ
    0.06
    è±ģè¾¾
    0.06
    ltr
    0.06
    lymp
    0.06
    æĿĤè´§
    0.06
    Activations Density 0.004%

    No Known Activations