© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16362
    Prev
    Next
    INDEX
    Explanations

    difficulty adjectives

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

    No Comments

    Negative Logits
    覆盖率
    -15.06
    罩
    -14.56
    arshal
    -14.31
    黎
    -13.94
     privacy
    -13.88
     Khal
    -13.19
     Gaz
    -13.06
    数据中心
    -13.06
     Privacy
    -13.00
    隐私
    -13.00
    POSITIVE LOGITS
    hammer
    19.75
    yre
    19.00
     nguyện
    18.88
    .subplots
    18.63
     Booker
    18.50
    ewire
    18.38
    utton
    18.38
    actor
    18.13
     Robertson
    18.00
    eut
    17.88
    Activations Density 0.599%

    No Known Activations