© 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. 9158
    Prev
    Next
    INDEX
    Explanations

    hexadecimal or byte sequences

    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
    azzo
    -0.08
    æİł
    -0.07
    grab
    -0.06
    ooth
    -0.06
     craw
    -0.06
    å¼ĢåıijåĴĮ
    -0.06
    å°ıé¹ı
    -0.06
    ç»ĵæĿŁä¹ĭåIJİ
    -0.06
     Maggio
    -0.06
    èĢ³æľµ
    -0.06
    POSITIVE LOGITS
    èį·
    0.08
    riel
    0.07
    çĺ¢
    0.07
    æ½Ń
    0.07
     cor
    0.07
    жан
    0.07
    ÑģиÑĤе
    0.07
    æ½Ł
    0.07
    ÏĦεÏį
    0.07
    ritos
    0.07
    Activations Density 0.006%

    No Known Activations