© 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. 32141
    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
    ç°
    -0.07
    çĻ»å½ķæŁ¥çľĭ
    -0.07
    _repr
    -0.06
    à¸Īุ
    -0.06
    af
    -0.06
    _der
    -0.06
    at
    -0.06
    illes
    -0.06
     Rhodes
    -0.06
    åĽĬ
    -0.06
    POSITIVE LOGITS
    岸
    0.08
    rega
    0.07
    viso
    0.07
    ELIT
    0.07
    TOT
    0.07
    èĬŃ
    0.07
    ä¸īæĿ¡
    0.07
    åĪĨæ°´
    0.07
    ften
    0.07
    æĪı
    0.07
    Activations Density 0.010%

    No Known Activations