© 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. 50829
    Prev
    Next
    INDEX
    Explanations

    violence against people

    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
    è¾Ł
    -0.08
    plorer
    -0.08
    менÑĥ
    -0.07
    åŤ
    -0.07
    actoring
    -0.07
    ụi
    -0.07
    太è¡Į
    -0.07
     رس
    -0.07
    whelming
    -0.07
    å°ijåħĪ
    -0.07
    POSITIVE LOGITS
    èĩªå·±çļĦè¡Į为
    0.07
    æĺı
    0.07
    被害人
    0.07
    æĴ¬
    0.07
    å½ĵæĻļ
    0.07
    ÏĦει
    0.07
    æķħæĦı
    0.06
    å·¥ä½ľèģĮè´£
    0.06
    æĿĢ害
    0.06
    è¡Į为人
    0.06
    Activations Density 0.043%

    No Known Activations