© 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. 12666
    Prev
    Next
    INDEX
    Explanations

    description, summary, background, notes

    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
    ainter
    -0.08
    说ä¸įå®ļ
    -0.08
    æĹłç¼ĺ
    -0.08
    ç¼Ī
    -0.08
    rego
    -0.08
    _AMD
    -0.07
     comunque
    -0.07
    utory
    -0.07
     defaultMessage
    -0.07
    ipop
    -0.07
    POSITIVE LOGITS
    åľ¨è¿Ļ个è¿ĩç¨ĭä¸Ń
    0.10
     afterward
    0.10
     dabei
    0.09
     afterwards
    0.08
    æĢ»ç»ĵç»ıéªĮ
    0.07
    æķ´ä¸ªè¿ĩç¨ĭ
    0.07
    注æĦıäºĭ项
    0.07
     resulting
    0.07
     hasilnya
    0.07
    ä¿Ŀè¯ģåħ¶
    0.07
    Activations Density 0.364%

    No Known Activations