© 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. 27278
    Prev
    Next
    INDEX
    Explanations

    god, humanity, and the world

    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
    åªĽ
    -0.08
     oneself
    -0.08
    åĴĮåIJĮåѦ
    -0.08
    è¿ĶåĽŀåĪĹ表
    -0.08
    accio
    -0.08
     frisch
    -0.07
    åIJĮåѦéĥ½
    -0.07
    resher
    -0.07
    RICT
    -0.07
    漪
    -0.07
    POSITIVE LOGITS
    åľ°çIJĥä¸Ĭ
    0.08
     worldwide
    0.08
    éģįå¸ĥ
    0.08
     billions
    0.07
    _seed
    0.07
    æľīçĶŁ
    0.07
    æķ£å¸ĥ
    0.07
     destined
    0.07
    åĥıä½ł
    0.07
     suffering
    0.07
    Activations Density 0.101%

    No Known Activations