© 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. 21759
    Prev
    Next
    INDEX
    Explanations

    religious beliefs and doctrines

    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
    æľīåĬł
    -0.08
    尽责
    -0.08
    èĬ·
    -0.08
    iore
    -0.08
    upert
    -0.08
    àªŃ
    -0.07
    IEL
    -0.07
    inha
    -0.07
    éĨį
    -0.07
    æŁļ
    -0.07
    POSITIVE LOGITS
    é¦ĸé¢Ĩ
    0.07
    åĽ¢ä¼Ļ
    0.07
     beliefs
    0.07
     doctrines
    0.07
    ä¸»å¼ł
    0.07
    æŀģ端
    0.07
    æľ«æĹ¥
    0.07
    è¿Ŀæ³ķ
    0.07
     views
    0.06
    _PROTO
    0.06
    Activations Density 0.048%

    No Known Activations