© 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. 21023
    Prev
    Next
    INDEX
    Explanations

    date, week, size extraction

    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
    /cop
    -0.08
    žd
    -0.07
    apl
    -0.07
    qli
    -0.07
    TimeString
    -0.07
    _SUS
    -0.07
    ÛĮÚº
    -0.07
    ä¿
    -0.07
    åĬĽä½ľ
    -0.07
     convict
    -0.07
    POSITIVE LOGITS
    kle
    0.07
    اÙĦا
    0.07
    leos
    0.07
    anger
    0.06
    кÑĢа
    0.06
    çĬ
    0.06
    hell
    0.06
    elden
    0.06
    ONO
    0.06
    busters
    0.06
    Activations Density 0.004%

    No Known Activations