© 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. 15735
    Prev
    Next
    INDEX
    Explanations

    say radiation

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

    No Comments

    Negative Logits
     BUFF
    -19.38
    зв
    -17.63
     getConnection
    -17.50
     pBuffer
    -17.25
    olina
    -16.75
    ца
    -16.75
    empo
    -16.63
     Rück
    -16.38
    ennessee
    -16.25
     buffers
    -16.13
    POSITIVE LOGITS
     Ray
    18.50
     Radiation
    17.25
    Ray
    17.13
     radiation
    17.13
    佗
    16.38
     irradi
    16.13
    治疗
    16.00
     ray
    15.56
    放射
    15.13
    照射
    14.94
    Activations Density 0.037%

    No Known Activations