© 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. 15687
    Prev
    Next
    INDEX
    Explanations

    say AD

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

    No Comments

    Negative Logits
    柴
    -18.88
    虾
    -18.50
    tram
    -17.38
    sgi
    -17.25
    trait
    -16.88
    坯
    -16.88
    小额
    -16.88
    AuthService
    -16.75
    ibus
    -16.63
    枕
    -16.50
    POSITIVE LOGITS
     AD
    27.75
    Ad
    25.88
    -ad
    25.75
     Ad
    25.38
    AD
    24.88
    adc
    24.00
    _AD
    23.88
     ad
    23.63
    _ad
    23.25
    _ads
    23.13
    Activations Density 0.241%

    No Known Activations