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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13964
    Prev
    Next
    INDEX
    Explanations

    say "storage"

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

    No Comments

    Negative Logits
    analysis
    -17.63
    分析
    -17.25
     analysis
    -17.13
    _analysis
    -16.50
     analyses
    -16.50
    -analysis
    -16.38
     analys
    -16.25
     análisis
    -16.13
    泗
    -15.88
    efd
    -15.56
    POSITIVE LOGITS
    存储
    20.88
     access
    20.38
    access
    19.75
     accessing
    19.50
     drives
    19.38
     drive
    19.25
     accesses
    19.13
    访问
    19.13
     Access
    19.00
    drive
    18.75
    Activations Density 0.169%

    No Known Activations