© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1357
    Prev
    Next
    INDEX
    Explanations

    variable

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

    No Comments

    Negative Logits
    变量
    -47.00
     variables
    -45.75
     variable
    -45.00
    Variables
    -44.25
    variables
    -44.25
     Variables
    -43.25
    Variable
    -43.00
    variable
    -43.00
     Variable
    -41.00
    -variable
    -38.75
    POSITIVE LOGITS
    蜂蜜
    17.38
    电工
    16.38
    墨
    15.88
    .aws
    15.81
    密码
    15.19
     Columbus
    14.63
    Swagger
    14.56
    博客
    14.56
    蜜蜂
    14.50
    mite
    14.31
    Activations Density 0.092%

    No Known Activations