© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15558
    Prev
    Next
    INDEX
    Explanations

    say "calcium"

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

    No Comments

    Negative Logits
    薰
    -18.25
     Murdoch
    -17.88
    ESPN
    -17.63
    茂
    -17.38
    reur
    -17.00
     Roose
    -16.88
    鹜
    -16.88
    zie
    -16.88
    预言
    -16.63
    自动化
    -16.50
    POSITIVE LOGITS
    钙
    29.00
     calcium
    28.13
     Calcium
    26.25
    calc
    26.13
    (calc
    23.38
    Calc
    23.25
     limestone
    23.13
     carbonate
    22.75
    石膏
    21.50
     calc
    21.13
    Activations Density 0.135%

    No Known Activations