© 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. 64591
    Prev
    Next
    INDEX
    Explanations

    moment of inertia and geometric properties

    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
     signaling
    -0.07
     lấn
    -0.07
    çĶµå¹³
    -0.07
    éĩİ
    -0.07
    اÙĤ
    -0.07
     events
    -0.07
    -hide
    -0.07
     signalling
    -0.07
    ofi
    -0.07
    解çłģ
    -0.06
    POSITIVE LOGITS
    -spin
    0.08
    éĺ»åĬĽ
    0.08
     inertia
    0.08
    (inertia
    0.08
     bob
    0.08
    转åĬ¨
    0.08
    Moment
    0.08
    धार
    0.08
    ertia
    0.07
    moment
    0.07
    Activations Density 0.004%

    No Known Activations