© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14521
    Prev
    Next
    INDEX
    Explanations

    [W] => [W]

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

    No Comments

    Negative Logits
    AIL
    -21.25
    DG
    -19.50
    EI
    -19.38
    ail
    -19.25
    HD
    -18.38
    inus
    -18.25
     Deer
    -18.13
    iname
    -18.13
    holm
    -18.13
    AIT
    -18.13
    POSITIVE LOGITS
     Bre
    15.19
     Bru
    14.00
    破
    13.75
     bre
    13.19
    uve
    13.13
    复活
    13.06
    跳出
    13.00
     word
    12.63
     Word
    12.56
     rupture
    12.50
    Activations Density 0.006%

    No Known Activations