© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    say 1

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

    No Comments

    Negative Logits
    ément
    -20.13
    ems
    -18.88
    百度
    -18.63
    én
    -18.00
    anic
    -17.88
    ment
    -17.75
    ads
    -17.38
    uit
    -17.38
    enet
    -17.25
     Gwen
    -17.13
    POSITIVE LOGITS
     Boone
    17.88
     ter
    14.19
     zie
    13.69
     coerce
    13.50
     Ter
    13.38
     topp
    13.25
    胛
    13.00
    交接
    12.94
    Prov
    12.69
     Doe
    12.63
    Activations Density 0.069%

    No Known Activations