© 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. 15602
    Prev
    Next
    INDEX
    Explanations

    say decrease

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

    No Comments

    Negative Logits
    isOpen
    -19.25
     isOpen
    -17.88
    擴
    -17.63
    拓展
    -17.38
    扩展
    -17.00
    addElement
    -16.63
    .isOpen
    -16.50
     Cand
    -15.75
     StringTokenizer
    -15.75
    镳
    -15.38
    POSITIVE LOGITS
    降
    34.50
    降低
    32.50
    下降
    32.50
    降幅
    31.50
     reduction
    30.13
    下滑
    30.00
     decrease
    29.88
    降到
    29.63
     reductions
    28.63
     decreasing
    28.13
    Activations Density 0.423%

    No Known Activations