© 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. 34566
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and rotation

    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
    olim
    -0.08
    ä¸ī份
    -0.07
    人马
    -0.07
    uentes
    -0.07
    åd
    -0.07
    éĩįä¿®
    -0.07
    对æķ´ä¸ª
    -0.07
    é«ĺçħ§
    -0.07
     долÑİ
    -0.07
    orest
    -0.06
    POSITIVE LOGITS
    rotate
    0.09
     rotated
    0.09
     rotation
    0.09
     Rotation
    0.09
    rot
    0.09
    æĹĭ转
    0.08
    .rotate
    0.08
    rotation
    0.08
    _rotation
    0.08
     rotations
    0.08
    Activations Density 0.010%

    No Known Activations