© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1145
    Prev
    Next
    INDEX
    Explanations

    [satellite] => [satellite]

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

    No Comments

    Negative Logits
    卫星
    -31.88
     satellite
    -31.88
     Satellite
    -31.25
     satellites
    -28.00
     Sal
    -23.50
    盐
    -22.88
    Sal
    -22.75
    GPS
    -22.63
    鹽
    -22.25
    (card
    -21.75
    POSITIVE LOGITS
    arma
    15.06
    英
    14.63
    琅
    14.31
    玹
    13.94
    京剧
    13.94
     computed
    13.75
    中药
    13.69
     Hull
    13.69
    Compute
    13.50
    Logic
    13.44
    Activations Density 0.043%

    No Known Activations