© 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. 19931
    Prev
    Next
    INDEX
    Explanations

    function calls with arguments

    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
    esy
    -0.07
    åĤ»
    -0.06
    yl
    -0.06
    ä½ľåģĩ
    -0.06
    orno
    -0.06
    é¦
    -0.06
    enf
    -0.06
    ig
    -0.06
    ut
    -0.06
    åģĩ
    -0.06
    POSITIVE LOGITS
    kund
    0.09
    apu
    0.08
     recons
    0.07
     fortuna
    0.07
    undu
    0.07
     повеÑĢ
    0.07
    éĿĴèįī
    0.07
    åĴĮéĩįçĤ¹
    0.07
    tÃł
    0.07
     Hutch
    0.07
    Activations Density 0.035%

    No Known Activations