© 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. 10584
    Prev
    Next
    INDEX
    Explanations

    Lorentz transformations equations

    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
    CommandEvent
    -0.08
    éľĨ
    -0.08
    urig
    -0.08
    unie
    -0.07
     Balai
    -0.07
    entina
    -0.07
    emy
    -0.07
    å¦ĤçĥŁ
    -0.07
     Brunswick
    -0.07
    PIPE
    -0.07
    POSITIVE LOGITS
     factor
    0.07
    åĽłåŃIJ
    0.07
     Lore
    0.07
    åĴĮä¿¡æģ¯
    0.07
     Profile
    0.07
     posture
    0.07
     наÑĢа
    0.07
    profile
    0.07
     profile
    0.06
     dilation
    0.06
    Activations Density 0.001%

    No Known Activations