© 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. 7495
    Prev
    Next
    INDEX
    Explanations

    angle measurement

    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
    æµģéĢļ
    -0.07
    åºŀ大
    -0.07
     обÑĬемом
    -0.07
    æ´»æĢ§
    -0.07
    èĩ´
    -0.07
    ç³»æķ°
    -0.06
    ä½ĵè´¨
    -0.06
    çī©è´¨çļĦ
    -0.06
    ç½²
    -0.06
    åĿ
    -0.06
    POSITIVE LOGITS
     angle
    0.17
     angles
    0.16
    angle
    0.15
    -angle
    0.15
     Angle
    0.15
    Angle
    0.15
    è§Ĵ度
    0.14
    _angle
    0.13
    çļĦè§Ĵ度
    0.13
    (angle
    0.12
    Activations Density 0.040%

    No Known Activations