© 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. 30750
    Prev
    Next
    INDEX
    Explanations

    church, religion, Christian

    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
    Ajax
    -0.07
    oriously
    -0.07
    iments
    -0.07
    Æ°á»Ľng
    -0.07
    å¦Ĥåħ¶
    -0.07
     sofist
    -0.07
    èİİ士
    -0.07
     Tết
    -0.07
    Mvc
    -0.06
     brut
    -0.06
    POSITIVE LOGITS
     religious
    0.12
    å®ĹæķĻ
    0.12
     sacram
    0.11
     Religious
    0.10
    ç¥Ī祷
    0.10
    religious
    0.10
    çļĪä¾Ŀ
    0.10
    æķĻå¾Ĵ
    0.10
     church
    0.10
    åŁºçĿ£æķĻ
    0.10
    Activations Density 0.729%

    No Known Activations