© 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. 24259
    Prev
    Next
    INDEX
    Explanations

    department

    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
    plex
    -0.07
    minente
    -0.07
    åģľæľº
    -0.07
    ocal
    -0.07
    ç£
    -0.07
    æļĹ
    -0.07
    å¾ģ
    -0.07
    aine
    -0.07
    PropertyDescriptor
    -0.06
    etes
    -0.06
    POSITIVE LOGITS
     СоглаÑģно
    0.07
    æł¹æį®åħ¶
    0.07
    æķ¬
    0.07
    wür
    0.06
    æľ¬é¢ĺ
    0.06
    é¡Į
    0.06
    VN
    0.06
    人类çļĦ
    0.06
    èĤĸ
    0.06
    åı£çļĦ
    0.06
    Activations Density 0.001%

    No Known Activations