© 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. 20088
    Prev
    Next
    INDEX
    Explanations

    Christian denominations and theology

    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
    izard
    -0.07
    .ravel
    -0.07
    edes
    -0.07
    å¸Ĥéķ¿
    -0.07
     Karn
    -0.07
    JsonValue
    -0.07
    блÑĸ
    -0.07
     Rajasthan
    -0.07
    aign
    -0.07
    irror
    -0.07
    POSITIVE LOGITS
     doctr
    0.11
     congreg
    0.09
     orthodox
    0.09
     doctrine
    0.09
     exe
    0.09
     sacram
    0.09
     doctrines
    0.08
    æŃ£ç»Ł
    0.08
     theological
    0.08
     theology
    0.08
    Activations Density 0.216%

    No Known Activations