© 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. 12627
    Prev
    Next
    INDEX
    Explanations

    math and code fragments

    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
    éħįåIJĪ
    -0.07
    _SPEC
    -0.07
    odb
    -0.07
    ENCI
    -0.07
    fare
    -0.07
    .extensions
    -0.07
    çļĦç¡®æĺ¯
    -0.07
    ÙĦد
    -0.07
     truc
    -0.07
    ç¼ĵç¼ĵçļĦ
    -0.06
    POSITIVE LOGITS
    ihu
    0.07
    olumn
    0.07
    illard
    0.07
    alls
    0.07
    奸
    0.07
    Vo
    0.06
     Yol
    0.06
    .Ref
    0.06
    ç¥
    0.06
    æŃ¤åľ°
    0.06
    Activations Density 0.011%

    No Known Activations