© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2040
    Prev
    Next
    INDEX
    Explanations

    religion and God

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bible
    -0.32
     scaleX
    -0.29
    å®ĹæķĻ
    -0.28
    VertexBuffer
    -0.26
     ++;↵
    -0.26
     Religious
    -0.25
    ï·º
    -0.24
     religious
    -0.24
     gunmen
    -0.23
    religious
    -0.23
    POSITIVE LOGITS
    è¿Ļä¸ªåľ°åĽ¾
    0.28
     nargin
    0.27
    æ±Ĩ
    0.27
    å¼ĢèįĴ
    0.26
    çļĦ带é¢Ĩ
    0.24
    ICTURE
    0.23
    ç¨Ĺ
    0.22
     pupper
    0.21
     molec
    0.21
    è´«åĽ°äººåı£
    0.21
    Activations Density 1.979%

    No Known Activations