© 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. 15311
    Prev
    Next
    INDEX
    Explanations

    say "uppercase acronyms"

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

    No Comments

    Negative Logits
    ar
    -28.88
    rir
    -28.25
    r
    -26.50
    rar
    -26.50
    AR
    -25.75
    rer
    -25.25
     ar
    -24.25
    .ar
    -24.13
     Ar
    -23.38
    urar
    -23.13
    POSITIVE LOGITS
    懈
    17.00
     Zac
    16.13
    莲花
    15.38
    窝
    14.50
    monkey
    14.31
    沸
    14.25
    蓼
    14.06
    甩
    14.00
     Tob
    13.94
    wid
    13.63
    Activations Density 0.026%

    No Known Activations