© 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. 15847
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/determiner

    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
    umah
    -0.07
     vij
    -0.07
    uert
    -0.07
    erma
    -0.07
    leid
    -0.07
    æĬ¤æ³ķ
    -0.07
    мали
    -0.06
    æĺ
    -0.06
    eite
    -0.06
    åĪĩå®ŀæĬĬ
    -0.06
    POSITIVE LOGITS
    群
    0.07
    群çļĦ
    0.07
     aforementioned
    0.07
    éĺħè¯»æľ¬æĸĩåīį
    0.07
     succeeding
    0.07
    cken
    0.07
    人å¤ļ
    0.07
    سبÙĤ
    0.07
    yal
    0.07
    zen
    0.07
    Activations Density 0.669%

    No Known Activations