© 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. 1096
    Prev
    Next
    INDEX
    Explanations

    say political

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

    No Comments

    Negative Logits
     storage
    -47.75
    存储
    -47.00
    Storage
    -44.25
     Storage
    -43.25
    storage
    -42.25
    储存
    -40.50
     store
    -40.25
    	store
    -39.50
    -storage
    -39.25
    储
    -38.75
    POSITIVE LOGITS
    政治
    19.88
    数学
    17.38
     Political
    16.63
     political
    16.38
     mathematic
    15.94
     Mathematical
    15.63
    Math
    15.31
    的政治
    15.31
    三角
    15.25
     Politics
    14.75
    Activations Density 0.180%

    No Known Activations