© 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. 12316
    Prev
    Next
    INDEX
    Explanations

    closest answer

    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
    ç½ijç«Ļ导èĪª
    -0.09
    inti
    -0.08
     volna
    -0.08
    檬
    -0.08
    å¼¥
    -0.08
    ARN
    -0.08
    èĢĮæĺĵ
    -0.08
    ÐĽÐŀÐĴ
    -0.08
    cov
    -0.08
    /dat
    -0.08
    POSITIVE LOGITS
    opsis
    0.06
    解é¢ĺ
    0.06
    åĴĮæĦıä¹ī
    0.06
    åİŁåĽłåľ¨äºİ
    0.06
    terer
    0.06
    0.06
    arif
    0.06
    æĺĩ
    0.05
     Ñģов
    0.05
    0.05
    Activations Density 0.001%

    No Known Activations