© 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. 16040
    Prev
    Next
    INDEX
    Explanations

    noble titles

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

    No Comments

    Negative Logits
    _plane
    -21.88
    planes
    -21.25
     plane
    -20.38
    plane
    -19.63
     planes
    -19.50
    蝴蝶
    -19.50
    平面
    -18.75
    European
    -18.63
    Western
    -18.63
    Plane
    -18.63
    POSITIVE LOGITS
     GRAT
    16.75
     count
    16.25
     Counts
    15.94
     Count
    15.38
    Count
    15.38
     honorary
    15.13
    税费
    14.56
    sson
    14.50
    税
    14.38
    社区
    14.38
    Activations Density 0.191%

    No Known Activations