© 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. 62488
    Prev
    Next
    INDEX
    Explanations

    business and finance concepts

    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
    åĽłä¸ºåıªæľī
    -0.08
    åĽłä¸ºåħ¶
    -0.07
    åĽłä¸ºå®ĥ
    -0.07
    åĽłä¸ºè¿Ļ个
    -0.07
    åĽłä¸ºä»ĸ
    -0.07
    because
    -0.07
    ounced
    -0.07
    Bợi
    -0.07
    åĽłçĤº
    -0.07
     because
    -0.07
    POSITIVE LOGITS
    ä»İèĢĮ
    0.09
     thus
    0.07
    ä»İèĢĮå½±åĵį
    0.07
    velt
    0.07
    顺é£İ
    0.07
    å¿Ĺæĺİ
    0.07
     potenci
    0.07
     поÑĤенÑĨи
    0.07
    æ½ľåľ¨çļĦ
    0.07
    顺便
    0.07
    Activations Density 0.074%

    No Known Activations