© 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. 919
    Prev
    Next
    INDEX
    Explanations

    say German places

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

    No Comments

    Negative Logits
     Sloven
    -35.50
    阿根廷
    -34.00
     Buenos
    -33.25
     Croatian
    -33.00
    奥地利
    -32.75
     Argentine
    -32.25
     Yugosl
    -31.50
     Serbian
    -30.88
     Hungarian
    -30.00
     Albania
    -30.00
    POSITIVE LOGITS
    涿
    22.25
    燕
    18.63
     Sax
    18.13
    北
    17.88
    廊坊
    17.50
    .ix
    16.88
    鄚
    16.63
    న
    16.50
    ��
    16.38
    白沙
    16.13
    Activations Density 0.087%

    No Known Activations