© 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. 1500
    Prev
    Next
    INDEX
    Explanations

    say "two-letter codes"

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

    No Comments

    Negative Logits
    SCRIPT
    -22.38
    HC
    -22.38
     ac
    -22.38
     HC
    -22.38
     RC
    -22.00
     Acc
    -21.75
    _ac
    -21.63
     arc
    -21.63
    acs
    -21.25
    -ac
    -21.13
    POSITIVE LOGITS
    anium
    17.63
     Matthews
    16.75
    mat
    16.00
     Matthew
    15.38
    uries
    15.13
    мат
    14.81
     unsuccessfully
    14.50
    -builder
    14.38
    mond
    14.13
    mast
    14.06
    Activations Density 0.378%

    No Known Activations