© 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. 1164
    Prev
    Next
    INDEX
    Explanations

    memory

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

    No Comments

    Negative Logits
    _memory
    -22.63
     memory
    -22.50
    内存
    -22.38
    -memory
    -22.25
     MEMORY
    -22.00
    MEMORY
    -21.50
    .memory
    -21.38
     Memory
    -21.00
    memory
    -20.50
    Memory
    -19.25
    POSITIVE LOGITS
    英超
    19.63
    iola
    16.63
     Sheffield
    16.38
    Politics
    15.88
    钢厂
    15.69
    科学
    15.69
     XHTML
    15.69
     Politics
    15.38
     political
    15.31
     TOOL
    15.31
    Activations Density 0.073%

    No Known Activations