© 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. 65203
    Prev
    Next
    INDEX
    Explanations

    quaternion rotations and transforms

    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
    åĹĵåŃIJ
    -0.07
    .nextInt
    -0.06
    人影
    -0.06
    çĶµè·¯åĽ¾
    -0.06
    æļĹ访
    -0.06
    åĪĴ线
    -0.06
    ribbon
    -0.06
     fluct
    -0.06
     ess
    -0.06
     types
    -0.06
    POSITIVE LOGITS
     Quaternion
    0.10
    Quaternion
    0.10
    æĹĭ
    0.10
    姿
    0.09
     rotations
    0.09
    æĹĭ转
    0.09
     axes
    0.09
     rotates
    0.09
     quaternion
    0.09
    .rotation
    0.08
    Activations Density 0.044%

    No Known Activations