© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15588
    Prev
    Next
    INDEX
    Explanations

    say countries

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

    No Comments

    Negative Logits
    funcs
    -15.50
    不明白
    -14.19
    tering
    -14.13
    (Contact
    -14.06
    .setRequestHeader
    -14.06
    俱乐部
    -14.06
    imeter
    -13.75
    锥
    -13.75
    utow
    -13.75
    PRIMARY
    -13.69
    POSITIVE LOGITS
    挪威
    29.88
     Kerala
    27.38
     Scotland
    27.13
     Finnish
    27.13
    葡萄牙
    26.38
     Scottish
    25.88
     Louisiana
    25.38
     Icelandic
    25.25
    南非
    25.25
     Norwegian
    25.13
    Activations Density 0.589%

    No Known Activations