© 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. 40113
    Prev
    Next
    INDEX
    Explanations

    quoting or citation

    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
    plotlib
    -0.09
    ../../../
    -0.08
    pace
    -0.08
    imetr
    -0.08
    aphore
    -0.08
    ../../
    -0.08
    ستÙĬ
    -0.08
    -0.08
     Unidos
    -0.08
    chini
    -0.08
    POSITIVE LOGITS
    zelf
    0.08
    à¹Ģวียà¸Ļ
    0.08
    족
    0.07
    εÏĦαι
    0.07
    asse
    0.07
    itial
    0.07
    ERENCE
    0.07
    Ñıд
    0.07
    åijIJ
    0.07
     ëĤĺìĦľ
    0.07
    Activations Density 0.021%

    No Known Activations