© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16334
    Prev
    Next
    INDEX
    Explanations

    say importance

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

    No Comments

    Negative Logits
    气血
    -17.63
    博会
    -16.63
     airflow
    -16.63
    Inspectable
    -16.13
     Gaz
    -16.00
    .createClass
    -15.63
     softened
    -15.63
    LinkId
    -15.50
     gaz
    -15.31
    羡慕
    -15.06
    POSITIVE LOGITS
    .priority
    26.13
     priority
    24.25
     importance
    24.00
    priority
    23.13
     priorities
    22.50
    _priority
    22.38
    -import
    22.25
    关键
    22.25
    Priority
    22.00
     Priority
    22.00
    Activations Density 0.299%

    No Known Activations