© 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. 2758
    Prev
    Next
    INDEX
    Explanations

    say "addr"

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

    No Comments

    Negative Logits
    -bin
    -16.50
    絲
    -15.69
     optics
    -15.38
     mutants
    -15.38
    _simulation
    -15.13
    шки
    -15.00
     colon
    -15.00
    (per
    -14.94
    改革
    -14.88
    检验
    -14.81
    POSITIVE LOGITS
     addr
    60.25
    (addr
    54.00
    addr
    54.00
     Addr
    52.75
    .addr
    52.75
    Addr
    52.50
    	addr
    50.50
    _addr
    47.00
    .Addr
    42.00
    _ADDR
    40.25
    Activations Density 0.022%

    No Known Activations