© 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. 22010
    Prev
    Next
    INDEX
    Explanations

    incorporated by reference

    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
    订éĺħä¸ĵæłı
    -0.08
    ILA
    -0.08
    æĸ°ä¹¦æݨèįIJ
    -0.07
    ç²Ĵ
    -0.07
    erry
    -0.07
    oron
    -0.07
    elis
    -0.07
    indel
    -0.07
    æݨèįIJæľ¬ä¹¦
    -0.07
    :Add
    -0.07
    POSITIVE LOGITS
    /cache
    0.08
     URL
    0.07
    asta
    0.07
    /browse
    0.07
    URL
    0.07
     citation
    0.07
    æĦĪ
    0.06
    ç«Ļ
    0.06
     Fors
    0.06
    /archive
    0.06
    Activations Density 0.044%

    No Known Activations