© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14811
    Prev
    Next
    INDEX
    Explanations

    coral

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INST
    -16.63
    奚
    -16.50
    验证
    -16.50
    库里
    -16.38
    objs
    -16.00
     Fulton
    -15.50
    ('${
    -15.44
    ὴ
    -15.38
     Vladimir
    -15.31
    .paths
    -15.31
    POSITIVE LOGITS
    珊瑚
    17.25
    ree
    16.50
     Reef
    16.13
     Coral
    15.69
     reef
    15.06
    cal
    14.19
    �
    14.00
     Calendar
    13.56
     calc
    13.38
     grant
    13.38
    Activations Density 0.096%

    No Known Activations