© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2088
    Prev
    Next
    INDEX
    Explanations

    荣

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

    No Comments

    Negative Logits
    _cur
    -22.75
    Cur
    -21.00
    [cur
    -20.38
    (cur
    -20.13
    CUR
    -19.63
    代
    -18.88
    cur
    -18.63
    曲
    -18.50
     Cur
    -18.13
    Fil
    -18.13
    POSITIVE LOGITS
     reg
    47.50
    (reg
    46.00
    荣
    44.25
    reg
    44.00
     Reg
    41.75
    	reg
    41.75
    Reg
    40.50
     REG
    40.00
    REG
    37.75
    _reg
    37.00
    Activations Density 0.029%

    No Known Activations