© 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. 20564
    Prev
    Next
    INDEX
    Explanations

    railway tracks and maintenance

    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
    æ²¹çĥŁæľº
    -0.07
    åĨħèĥĨ
    -0.07
    éĢıæĺİçļĦ
    -0.07
    åĬ³åĬ¨ä»²è£ģ
    -0.07
     stap
    -0.07
     zip
    -0.07
    ä¿Ŀé²ľ
    -0.07
     respir
    -0.06
    å½ĵ羣
    -0.06
    gewater
    -0.06
    POSITIVE LOGITS
    ç»´æĬ¤
    0.09
     railway
    0.09
     upkeep
    0.08
     maintenance
    0.08
     Maintenance
    0.08
    ç»´æĬ¤åĴĮ
    0.08
     roadway
    0.08
    éĵģè·¯
    0.07
    è¡Į人
    0.07
    ä¸İç»´æĬ¤
    0.07
    Activations Density 0.011%

    No Known Activations