© 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. 1661
    Prev
    Next
    INDEX
    Explanations

    wear and tear

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

    No Comments

    Negative Logits
     Writing
    -36.50
     writing
    -34.50
     Write
    -34.00
    Write
    -33.50
    写作
    -33.25
    Writing
    -32.75
    -writing
    -31.63
     write
    -31.25
    write
    -30.88
    Writer
    -30.88
    POSITIVE LOGITS
    alon
    15.19
    酸
    14.75
    edm
    14.06
    迢
    13.06
    osphate
    12.63
     suck
    12.63
    PTY
    12.63
    طن
    12.56
    uhn
    12.38
    zm
    12.25
    Activations Density 0.639%

    No Known Activations