© 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. 14333
    Prev
    Next
    INDEX
    Explanations

    say mining

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

    No Comments

    Negative Logits
    _Interface
    -19.00
    插
    -19.00
    插入
    -17.75
    インター�
    -17.50
    _INTERFACE
    -16.38
     interface
    -15.56
    warts
    -15.31
    悱
    -15.19
    _interfaces
    -15.13
    interface
    -14.94
    POSITIVE LOGITS
     mining
    38.00
    矿
    37.50
     mines
    36.75
    矿山
    36.25
     Mining
    35.50
     mine
    34.75
    矿业
    34.75
    采矿
    34.50
    矿区
    34.25
     mined
    33.25
    Activations Density 0.546%

    No Known Activations