© 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. 15773
    Prev
    Next
    INDEX
    Explanations

    grammatical number

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

    No Comments

    Negative Logits
    湛江
    -18.63
    -HT
    -17.00
     Mobility
    -16.88
    -Mobile
    -16.38
    Cold
    -16.25
     chilled
    -16.25
    交通安全
    -16.13
    口岸
    -15.81
     Hayward
    -15.69
    泰安
    -15.69
    POSITIVE LOGITS
     singular
    20.88
     Singular
    19.50
     sing
    19.25
    sing
    18.63
    _singular
    18.50
    Sing
    17.75
     plural
    17.75
     pron
    17.63
    singular
    17.25
    pron
    17.13
    Activations Density 0.094%

    No Known Activations