© 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. 32061
    Prev
    Next
    INDEX
    Explanations

    time periods and measurements

    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
    pee
    -0.09
    çĽ²
    -0.08
    pees
    -0.08
    antt
    -0.07
    åľ¨å®ĮæĪIJ
    -0.07
    ä¹ĭåīij
    -0.07
    atted
    -0.07
    ächt
    -0.07
    Äģj
    -0.07
    cape
    -0.07
    POSITIVE LOGITS
    çİĭ大
    0.07
    寿åij½
    0.07
    ervals
    0.07
     periods
    0.06
    è¾ĥéķ¿çļĦ
    0.06
    crete
    0.06
    ativer
    0.06
    åĭķ
    0.06
    uga
    0.06
     contado
    0.06
    Activations Density 0.005%

    No Known Activations