© 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. 15681
    Prev
    Next
    INDEX
    Explanations

    hard suffixes

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

    No Comments

    Negative Logits
     addObserver
    -16.50
     DST
    -15.94
     CommandType
    -15.31
     Observation
    -15.06
    .gridView
    -14.75
    观测
    -14.44
     Observatory
    -14.19
    灵敏
    -14.19
    壮观
    -14.19
     Obs
    -14.00
    POSITIVE LOGITS
    rock
    16.88
    ware
    16.75
     plastics
    16.50
    pla
    16.00
     keras
    15.94
    erp
    15.81
     Bord
    15.63
    awns
    15.50
    _coin
    15.44
    陸
    15.44
    Activations Density 0.041%

    No Known Activations