© 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. 64363
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    é¢Ŀ
    -0.07
    ä½ı
    -0.07
    æĶ¯
    -0.07
    ëł¹
    -0.07
    leder
    -0.07
     Supporting
    -0.07
    setting
    -0.07
    路边çļĦ
    -0.07
    egend
    -0.06
    .tt
    -0.06
    POSITIVE LOGITS
    åħ¨ç§°
    0.12
     stands
    0.11
     acronym
    0.10
     stand
    0.09
     abbreviation
    0.09
    stands
    0.08
     shorthand
    0.08
    ยà¹Īà¸Ń
    0.08
     abbrev
    0.08
     initials
    0.08
    Activations Density 0.167%

    No Known Activations