© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39409
    Prev
    Next
    INDEX
    Explanations

    is/are followed by descriptive words

    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
    å°±æĺ¯æľĢ好çļĦ
    -0.07
    panse
    -0.07
    czyk
    -0.07
    ä¸į论æĺ¯
    -0.07
    ÑĪенко
    -0.07
    å¹¶è¿Ľ
    -0.07
     ÙħعÙĦ
    -0.07
    ãģ¾ãģ¾ãģ§
    -0.07
    并åıĬæŶ
    -0.06
    使å®ĥ
    -0.06
    POSITIVE LOGITS
     therefore
    0.10
    åĽłæѤ
    0.08
     daher
    0.08
    /or
    0.07
    ä¸İ伦
    0.07
    åł´åIJĪ
    0.07
     moreover
    0.07
     thus
    0.07
     hence
    0.07
    åĽłæŃ¤åľ¨
    0.07
    Activations Density 0.353%

    No Known Activations