© 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. 42602
    Prev
    Next
    INDEX
    Explanations

    cults, worship, rituals, temples, offering

    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
    gj
    -0.07
     sall
    -0.07
     Brus
    -0.07
    dsn
    -0.06
    OrFail
    -0.06
     telegram
    -0.06
     ferrovi
    -0.06
     diplom
    -0.06
    emente
    -0.06
    æºľ
    -0.06
    POSITIVE LOGITS
    ç¥Ńç¥Ģ
    0.12
    ç¥Ģ
    0.12
    èĻĶè¯ļ
    0.11
    é¦Ļçģ«
    0.11
     worship
    0.11
     worsh
    0.11
     rituals
    0.11
    仪å¼ı
    0.10
    æķ¬çķı
    0.10
     ritual
    0.10
    Activations Density 0.043%

    No Known Activations