© 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. 12131
    Prev
    Next
    INDEX
    Explanations

    prepositions and ordinal indicators

    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
    çIJĨ解为
    -0.07
    è¿Ļç§įçݰ象
    -0.07
    ongo
    -0.07
    åĽł
    -0.06
    _generic
    -0.06
    ific
    -0.06
     determinato
    -0.06
    çĮľä½łåĸľæ¬¢
    -0.06
    éĩįæķ´
    -0.06
    æĸ°ä¹¦æݨèįIJ
    -0.06
    POSITIVE LOGITS
     both
    0.09
    both
    0.07
     ver
    0.07
    (ver
    0.07
    ÑĢина
    0.07
    ude
    0.07
     latter
    0.07
     Both
    0.07
    gger
    0.07
    kker
    0.07
    Activations Density 0.012%

    No Known Activations