© 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. 15661
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

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

    No Comments

    Negative Logits
    qu
    -34.00
    QU
    -33.00
    Qu
    -32.50
    ｑ
    -32.25
     Qu
    -32.25
     QU
    -31.38
    qd
    -31.25
    qh
    -30.88
    _qu
    -30.38
    *q
    -30.00
    POSITIVE LOGITS
    晶
    18.00
    ��
    17.25
    晶体
    17.13
    DEC
    16.50
    俸
    15.94
    GridColumn
    15.75
    挂
    15.56
    洹
    15.38
    (de
    15.31
    deo
    15.31
    Activations Density 1.310%

    No Known Activations