© 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. 61078
    Prev
    Next
    INDEX
    Explanations

    Newtonian physics and dynamics

    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
    ç²¾ç¥ŀåĪĨè£Ĥ
    -0.08
     proliferation
    -0.08
    å¾Ĺè¿ĩ
    -0.08
     Cocktail
    -0.07
    nyder
    -0.07
    éĢıåĩº
    -0.07
    æĮīæľŁ
    -0.07
     tenu
    -0.07
    igar
    -0.07
    plits
    -0.07
    POSITIVE LOGITS
    çī©ä½ĵ
    0.14
     Newton
    0.13
    çī©ä½ĵçļĦ
    0.12
    çīĽé¡¿
    0.11
    çī©çIJĨåѦ
    0.11
     motion
    0.11
     physics
    0.11
    è¿IJåĬ¨
    0.11
    åĬĽåѦ
    0.11
    å®ļå¾ĭ
    0.10
    Activations Density 0.035%

    No Known Activations