© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42517
    Prev
    Next
    INDEX
    Explanations

    geometric angles and directions

    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
    ä¸Ģè¨Ģ
    -0.08
    满天
    -0.07
    rawer
    -0.07
    è¿ĻæĬĬ
    -0.07
    èĦ±
    -0.07
    edos
    -0.07
     meta
    -0.07
    çĭ¬æłijä¸Ģå¸ľ
    -0.07
    æ»¡çľ¼
    -0.06
    å¨ģåĬĽ
    -0.06
    POSITIVE LOGITS
     azimuth
    0.08
     angle
    0.07
    åı³ä¾§
    0.07
     geom
    0.07
    zyn
    0.07
     angles
    0.07
    çļĦä¸Ģ侧
    0.07
    ä¸Ģ侧
    0.06
     perpendicular
    0.06
    沿
    0.06
    Activations Density 0.245%

    No Known Activations