© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62736
    Prev
    Next
    INDEX
    Explanations

    Torah, Moses, Law, Exodus

    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
    udies
    -0.07
    ezo
    -0.07
    ecto
    -0.07
     Thiá»ģn
    -0.07
    esia
    -0.07
    eza
    -0.07
    ancell
    -0.07
    ytter
    -0.07
    èĩªçŃ¹
    -0.07
    irro
    -0.07
    POSITIVE LOGITS
    仪
    0.08
    诫
    0.07
    èªĵ
    0.07
    é¢ģå¸ĥ
    0.07
     covenant
    0.07
     Moses
    0.07
    æŃ
    0.07
     prohib
    0.07
    ç¦ģ令
    0.07
    utenberg
    0.07
    Activations Density 0.013%

    No Known Activations