© 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. 15341
    Prev
    Next
    INDEX
    Explanations

    error messages or code constructs

    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
    çļĩåŁİ
    -0.07
    appropri
    -0.07
    оÑĩÑĮ
    -0.07
    stur
    -0.07
    orse
    -0.07
    annes
    -0.07
    åĿIJåĪ°
    -0.07
    _blocking
    -0.07
     ХаÑĢÑĮ
    -0.07
     manoe
    -0.07
    POSITIVE LOGITS
    Ø´Ùħ
    0.07
    lam
    0.07
    .cgi
    0.06
    à¸ĺรรม
    0.06
    plant
    0.06
    alba
    0.06
    jom
    0.06
     Uh
    0.06
    åĿĩ为
    0.06
    лага
    0.06
    Activations Density 0.003%

    No Known Activations