© 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. 17749
    Prev
    Next
    INDEX
    Explanations

    variables followed by assignments

    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
    nze
    -0.09
    æĭ¿ä¾Ĩ
    -0.08
    æĭ¿æĿ¥
    -0.08
    ãĥĥãĤº
    -0.08
    اÙģÙĦ
    -0.07
    æļ¨
    -0.07
     Renders
    -0.07
    åįĹæ¹ĸ
    -0.07
     illet
    -0.07
    StatusCode
    -0.07
    POSITIVE LOGITS
    éĢĤ
    0.07
     defined
    0.06
    åĪĨåĪ«ä¸º
    0.06
    close
    0.06
    =
    0.06
    icino
    0.06
    åħ³éĹŃçªĹåı£
    0.06
     terc
    0.05
     =
    0.05
    0.05
    Activations Density 0.009%

    No Known Activations