© 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. 57308
    Prev
    Next
    INDEX
    Explanations

    airport locations and terminals

    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
    ä»İ头
    -0.06
    acht
    -0.06
     period
    -0.06
    ahas
    -0.06
     timeline
    -0.06
    æĺ¯ä¸Ģ缴
    -0.06
    æķ´ä½ĵçļĦ
    -0.06
    ä¸Ģæ°Ķ
    -0.06
    eto
    -0.06
    acz
    -0.06
    POSITIVE LOGITS
    åIJŀåIJIJéĩı
    0.09
    à¸Ľà¸¥à¸²à¸¢à¸Ĺาà¸ĩ
    0.08
    åĩºåħ¥åı£
    0.08
    转è¿IJ
    0.08
    åį¸è½½
    0.08
     Terminal
    0.08
    byname
    0.08
    åı£çļĦ
    0.08
    rail
    0.08
     terminal
    0.08
    Activations Density 0.141%

    No Known Activations