© 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. 55690
    Prev
    Next
    INDEX
    Explanations

    ordering or ranking

    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
    æ¨
    -0.07
    åıĮ
    -0.07
    åıĮ线
    -0.07
    dbl
    -0.07
    åıĮåĢį
    -0.07
     Doppel
    -0.07
    _increment
    -0.07
    iak
    -0.07
    ru
    -0.07
     twin
    -0.07
    POSITIVE LOGITS
    æİĴåºı
    0.13
    顺åºı
    0.13
    çļĦ顺åºı
    0.13
     ranking
    0.12
     order
    0.12
     ranked
    0.12
     rankings
    0.11
    ä»İå°ıåĪ°å¤§
    0.11
    éłĨåºı
    0.11
    .order
    0.11
    Activations Density 0.041%

    No Known Activations