© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 982
    Prev
    Next
    INDEX
    Explanations

    say tropical

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

    No Comments

    Negative Logits
    镇江
    -24.13
     Croatian
    -18.25
    乙
    -18.13
    南京市
    -18.13
    江苏
    -18.00
    .js
    -18.00
    李白
    -18.00
    南京
    -17.88
     js
    -17.75
     Luigi
    -17.63
    POSITIVE LOGITS
    椰
    20.75
    海南省
    19.63
    热带
    18.00
     TX
    18.00
    槟
    17.88
    张家界
    17.75
    (reg
    17.63
     Tx
    17.63
     Reg
    17.25
    (tx
    17.13
    Activations Density 0.002%

    No Known Activations