© 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. 55428
    Prev
    Next
    INDEX
    Explanations

    village locations

    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
     Cities
    -0.10
    åŁİå¸Ĥ轨éģĵ交éĢļ
    -0.10
    åŁİå¸Ĥ建设
    -0.09
    ropp
    -0.09
    座åŁİå¸Ĥ
    -0.09
    大åݦ
    -0.09
    stadt
    -0.09
    è¿Ļ座åŁİå¸Ĥ
    -0.08
    åŁİå¸Ĥ管çIJĨ
    -0.08
    åŁİå¸Ĥè§ĦåĪĴ
    -0.08
    POSITIVE LOGITS
     rural
    0.14
     village
    0.13
     villagers
    0.11
     Rural
    0.11
    æĿijæ°ij
    0.11
     villages
    0.10
    åĨľæĿij
    0.10
    åĨľå®¶
    0.10
    乡æĿij
    0.10
    åľ¨åĨľæĿij
    0.10
    Activations Density 0.659%

    No Known Activations