© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 6982
    Prev
    Next
    INDEX
    Explanations

    list item numbers and punctuation

    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
    Negative Logits
    rys
    -0.08
    èµĮ
    -0.07
    __((
    -0.07
    PIP
    -0.07
     اÙĦصÙģ
    -0.06
    ÑģÑĤоиÑĤ
    -0.06
    âĢŀ
    -0.06
    ä¿¡æģ¯ä¸¾æĬ¥
    -0.06
    çŁŃçŁŃ
    -0.06
    acements
    -0.06
    POSITIVE LOGITS
    äºĮæĺ¯è¦ģ
    0.09
    äºĮæĺ¯
    0.09
    };
    0.09
    .";
    0.09
    );}
    0.08
    .);
    0.08
    åĽĽæĺ¯
    0.08
    ä¸īæĺ¯è¦ģ
    0.08
    (ii
    0.08
    ä¸ĭåIJĮ
    0.08
    Activations Density 0.178%

    No Known Activations