© 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. 65269
    Prev
    Next
    INDEX
    Explanations

    Christian and related concepts

    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
    деÑĨ
    -0.08
    quals
    -0.08
    abr
    -0.08
    ãĤĵãģ«
    -0.08
    older
    -0.07
    éĵ¶åŃIJ
    -0.07
    uelos
    -0.07
     óc
    -0.07
    lices
    -0.07
    ugh
    -0.07
    POSITIVE LOGITS
    -themed
    0.08
    å¾Ĵ
    0.08
    -Muslim
    0.08
    eno
    0.08
    -friendly
    0.08
    -leaning
    0.07
    ÑĦиÑĨи
    0.07
    -compatible
    0.07
    /AIDS
    0.07
    /non
    0.07
    Activations Density 0.045%

    No Known Activations