© 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. 2299
    Prev
    Next
    INDEX
    Explanations

    noun followed by a preposition or verb

    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
    èIJį
    -0.06
    .rar
    -0.06
     Colleg
    -0.06
    åį±éĻ©
    -0.06
    oven
    -0.06
    æī£
    -0.06
    å¾Ĺä¸Ģ
    -0.06
    kis
    -0.06
    oghi
    -0.06
    æĺİãģij
    -0.06
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.09
    æľ¬èº«
    0.09
     itself
    0.09
    æľ¬äººçļĦ
    0.08
    æľ¬äºº
    0.08
     themselves
    0.08
     bersangkutan
    0.08
     herself
    0.08
    è¿Ļ个æŶåĢĻ
    0.07
    emann
    0.07
    Activations Density 0.489%

    No Known Activations