© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    numbers and specific symbols

    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
    orny
    -0.07
    abet
    -0.07
    设æĸ½çļĦ
    -0.07
    ä¸ĭæĸ¹äºĮç»´çłģ
    -0.07
    sted
    -0.07
    borg
    -0.07
    é¦Ĩ
    -0.07
    edul
    -0.07
    ANDOM
    -0.07
    åķ
    -0.07
    POSITIVE LOGITS
     annual
    0.08
     convert
    0.07
    Ø·ÙĤ
    0.07
    年度
    0.07
    åŁºåľ°
    0.07
    æĪIJæ´»
    0.07
    è¡Į驶
    0.07
    åıĪå¿«
    0.06
    emet
    0.06
     converted
    0.06
    Activations Density 0.017%

    No Known Activations