© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1625
    Prev
    Next
    INDEX
    Explanations

    say programming terms

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

    No Comments

    Negative Logits
    气
    -41.25
    气体
    -38.00
     gas
    -37.25
    氣
    -37.25
    Gas
    -33.75
     Gas
    -32.25
    _gas
    -31.38
    口气
    -31.25
     gases
    -30.63
     GAS
    -29.38
    POSITIVE LOGITS
    XML
    17.63
    Java
    17.50
     Java
    16.88
    .sal
    16.50
     XML
    16.50
     EDIT
    16.38
    xml
    15.88
     xml
    15.44
     JAVA
    15.31
    java
    15.13
    Activations Density 0.078%

    No Known Activations