© 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. 32545
    Prev
    Next
    INDEX
    Explanations

    mass in physics contexts

    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
    åįķ身
    -0.09
    ÏĥÏĦι
    -0.08
    Scripts
    -0.07
    uren
    -0.07
    æĢİä¹Īçľĭ
    -0.07
    apper
    -0.07
    annel
    -0.07
    ARSE
    -0.07
     Schro
    -0.07
     Shel
    -0.06
    POSITIVE LOGITS
    osz
    0.09
    ÙĪا
    0.07
    ä¸įåIJĪæł¼çļĦ
    0.07
    ç¸
    0.07
     Sik
    0.07
    äºĶ次
    0.07
    æľīå¿ĥ人
    0.07
    .wait
    0.07
    igmoid
    0.07
    æݢ究
    0.07
    Activations Density 0.011%

    No Known Activations