© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    fancy Unicode letters

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

    No Comments

    Negative Logits
     Jiang
    -23.13
     Bulgarian
    -23.00
     Bulgaria
    -22.75
     Viet
    -22.50
    扬州
    -22.00
    Viet
    -21.75
    楚
    -21.00
     Greece
    -21.00
    江苏
    -20.88
     China
    -20.50
    POSITIVE LOGITS
     PCM
    20.75
    	script
    19.88
    ãi
    19.63
    红枣
    18.50
    琯
    18.25
     objc
    18.25
    PCM
    17.88
    xmin
    17.75
    xE
    17.50
    SCRIPT
    17.50
    Activations Density 0.007%

    No Known Activations