© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14797
    Prev
    Next
    INDEX
    Explanations

    prepositions

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

    No Comments

    Negative Logits
    othermal
    -17.38
    avings
    -17.13
    株洲
    -17.00
    peria
    -16.75
    卫视
    -16.63
    substr
    -16.00
    ibi
    -15.31
    了吗
    -15.31
    als
    -14.88
    oved
    -14.88
    POSITIVE LOGITS
     brig
    15.44
     brigade
    13.75
     Brig
    13.75
     Mà
    13.38
     unarmed
    13.06
     Pratt
    13.06
    �
    12.94
     verz
    12.88
    支部
    12.88
    nth
    12.81
    Activations Density 0.227%

    No Known Activations