© 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. 24985
    Prev
    Next
    INDEX
    Explanations

    negative attributes

    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
    æĢ»ç½²
    -0.08
    igente
    -0.07
     Aware
    -0.07
    ä½Ĩä¸įèĥ½
    -0.07
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    -0.07
    ÙĦاÛĮÙĨ
    -0.07
    æľīæīĢæĢĿ
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
    _numeric
    -0.07
    åı¯æľĽ
    -0.07
    POSITIVE LOGITS
    ãģĽãģ£ãģĭãģı
    0.10
     unnecessarily
    0.09
    ä¸įå¿ħè¦ģçļĦ
    0.08
    å®Ŀè´µçļĦ
    0.08
    太å¤ļ
    0.07
     terribly
    0.07
    èij©
    0.07
    就没
    0.06
    ä¸į说
    0.06
    太大
    0.06
    Activations Density 0.140%

    No Known Activations