© 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. 18819
    Prev
    Next
    INDEX
    Explanations

    secularism, atheism, neutral

    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
     congest
    -0.08
    åı¤å±ĭ
    -0.07
    nid
    -0.07
    باÙĦغ
    -0.07
    ä¸įåĢ¦
    -0.07
    ļĮ
    -0.07
    ä¸įåºĶæ±Ĥ
    -0.07
     xứng
    -0.07
    éļĶå¤ľ
    -0.07
    åĭ¤åĭī
    -0.07
    POSITIVE LOGITS
     secular
    0.13
     pagan
    0.10
     athe
    0.10
    ä¸ĸä¿Ĺ
    0.10
     neutrality
    0.10
     atheists
    0.09
     atheist
    0.09
     neutral
    0.09
    Neutral
    0.09
    ä¸Ńç«ĭ
    0.09
    Activations Density 0.145%

    No Known Activations