© 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. 49721
    Prev
    Next
    INDEX
    Explanations

    gravity and weight

    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
    ymar
    -0.08
    æĪĸåĪłéĻ¤
    -0.08
    æľµèĬ±
    -0.08
    -around
    -0.08
     boasts
    -0.07
    çĴ§
    -0.07
    udeau
    -0.07
     tơ
    -0.07
     ме
    -0.07
    antica
    -0.07
    POSITIVE LOGITS
    éĩįåĬĽ
    0.10
    bu
    0.09
    grav
    0.09
     gravity
    0.09
     weighing
    0.09
    ç«ĸ缴
    0.08
    gravity
    0.08
    ä½ĵéĩį
    0.08
    (weight
    0.08
     gravitational
    0.08
    Activations Density 0.005%

    No Known Activations