© 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. 22309
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
     desc
    -0.07
    éros
    -0.06
    zeh
    -0.06
    uelos
    -0.06
    xAA
    -0.06
    _CONFIGURATION
    -0.06
    wand
    -0.06
    寸
    -0.06
    åĪ°æĿ¥çļĦ
    -0.06
    ä¼Ĺå¿ĹæĪIJ
    -0.06
    POSITIVE LOGITS
     =
    0.08
    imme
    0.08
    bjerg
    0.08
    esser
    0.07
    éĺħ读åħ¨æĸĩ
    0.07
    apte
    0.07
    ãĤĤãģªãģĦ
    0.07
    itzer
    0.06
     اÙĦÙħÙĥر
    0.06
     reckon
    0.06
    Activations Density 0.008%

    No Known Activations