© 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. 38930
    Prev
    Next
    INDEX
    Explanations

    angles, rotation, and coordinates

    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
    é²ľè¡Ģ
    -0.08
    agal
    -0.08
    _adapter
    -0.08
    eku
    -0.07
    ä¸įå¾ĹäºĨ
    -0.07
    ç©¿äºĨ
    -0.07
    æ³īæ°´
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    èĩ³æѤ
    -0.07
    anita
    -0.07
    POSITIVE LOGITS
     rotation
    0.10
     Rotation
    0.09
     rotations
    0.09
    æĹĭ转
    0.08
    Rotation
    0.08
     вÑĢаÑīениÑı
    0.08
    rotation
    0.08
     Rot
    0.08
    imuth
    0.08
     rotational
    0.08
    Activations Density 0.008%

    No Known Activations