© 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. 2010
    Prev
    Next
    INDEX
    Explanations

    physics and math terms

    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
    æĪĸåĪłéĻ¤
    -0.08
    amid
    -0.07
    --+
    -0.07
    heber
    -0.07
    çīĪæľ¬
    -0.07
    มาà¸Ļ
    -0.07
    οÏħλ
    -0.07
    æĿ¥çļĦæŶåĢĻ
    -0.07
    heur
    -0.07
    iet
    -0.07
    POSITIVE LOGITS
    _EXT
    0.07
    cana
    0.06
    kozy
    0.06
    insel
    0.06
    abble
    0.06
    cessive
    0.06
    ä¸Ķæľī
    0.06
    ä¸Ķåľ¨
    0.06
    ised
    0.06
    ä¸Ķåħ·æľī
    0.06
    Activations Density 0.058%

    No Known Activations