© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15709
    Prev
    Next
    INDEX
    Explanations

    say inter

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

    No Comments

    Negative Logits
    花卉
    -15.44
     SEAL
    -14.06
    滹
    -13.94
    -secret
    -13.88
    rypton
    -13.88
    heads
    -13.75
    烯
    -13.75
    rypto
    -13.69
     blossom
    -13.63
     skulls
    -13.63
    POSITIVE LOGITS
    干预
    44.50
     interference
    41.75
    干涉
    40.50
     inter
    40.50
    Inter
    40.25
     Inter
    39.75
    inter
    39.00
     intervention
    38.75
     INTER
    38.00
     Intervention
    38.00
    Activations Density 0.306%

    No Known Activations