© 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. 62494
    Prev
    Next
    INDEX
    Explanations

    economic concepts and theory

    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
    移è¡Į
    -0.08
    åįİ侨
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    stro
    -0.07
    /Framework
    -0.07
    oom
    -0.07
    uito
    -0.07
    æīĽèµ·
    -0.07
    UserProfile
    -0.07
    é¡¹çĽ®åIJį称
    -0.07
    POSITIVE LOGITS
    åĴĮä¿¡æģ¯
    0.09
     imperfect
    0.08
    ä¿¡æģ¯çļĦ
    0.08
     costly
    0.08
    åįļå¼Ī
    0.08
     informational
    0.08
     information
    0.08
    ä¸Ńä»ĭ
    0.08
     inefficient
    0.08
    人ä¸İ人ä¹ĭéĹ´
    0.07
    Activations Density 0.017%

    No Known Activations