© 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
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 599
    Prev
    Next
    INDEX
    Explanations

    say Mars terms

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

    No Comments

    Negative Logits
    晋江
    -27.50
     Taiwanese
    -23.13
    漳州
    -21.75
    镇江
    -20.88
     Duterte
    -20.63
    福建省
    -20.50
     Filipino
    -20.13
    江门
    -19.63
     Gdańsk
    -19.00
     Taipei
    -18.88
    POSITIVE LOGITS
     Martian
    34.25
     Mars
    27.50
    火星
    26.63
    NASA
    22.75
    岩石
    22.38
    行星
    21.88
     NASA
    21.75
    地下水
    21.63
     rover
    21.50
    岩
    20.88
    Activations Density 0.155%

    No Known Activations