© 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. 49789
    Prev
    Next
    INDEX
    Explanations

    Bible and biblical content

    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
    elin
    -0.09
    otos
    -0.09
     recurs
    -0.07
    帽
    -0.07
    lacht
    -0.07
    agra
    -0.07
    idth
    -0.07
     POLITICO
    -0.07
    appa
    -0.07
    åĴĮåĨħ容
    -0.07
    POSITIVE LOGITS
    为ä¾Ŀæį®
    0.08
    -derived
    0.07
    hardt
    0.07
     Scripture
    0.07
     passages
    0.07
    对æĪij们çļĦ
    0.07
    æĺ¯ä¸Ģéĥ¨
    0.07
    ÏĦαι
    0.07
    lette
    0.07
     scripture
    0.07
    Activations Density 0.028%

    No Known Activations