© 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. 19405
    Prev
    Next
    INDEX
    Explanations

    gravity and related concepts

    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
    åŃIJéĩĮ
    -0.08
    ered
    -0.08
    nyder
    -0.07
    ullivan
    -0.07
    sWith
    -0.07
    RY
    -0.07
    ãĥ£
    -0.07
    tern
    -0.07
    oyer
    -0.07
    leman
    -0.07
    POSITIVE LOGITS
    wiÅĽcie
    0.09
    ÑģÑĮ
    0.09
    a
    0.08
    wort
    0.08
    а
    0.08
    erty
    0.08
    ÏĤ
    0.08
    idence
    0.07
    istrate
    0.07
    Ù°
    0.07
    Activations Density 0.004%

    No Known Activations