© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14987
    Prev
    Next
    INDEX
    Explanations

    say "no u"

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

    No Comments

    Negative Logits
    u
    -32.25
    -u
    -28.63
    uzu
    -27.13
    uur
    -26.75
    *u
    -26.75
    ulus
    -26.63
     u
    -26.13
    ulu
    -25.88
    ul
    -25.75
    ,u
    -25.38
    POSITIVE LOGITS
    揩
    16.38
    钖
    15.88
    сти
    15.81
    idades
    15.69
    燮
    15.06
    铰
    14.81
    堰
    14.69
    arih
    14.13
    zag
    14.06
    ocker
    14.00
    Activations Density 1.232%

    No Known Activations