© 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. 15342
    Prev
    Next
    INDEX
    Explanations

    say abbreviations

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

    No Comments

    Negative Logits
    dess
    -25.75
    Jess
    -24.50
    罗斯
    -24.25
    osis
    -23.38
     Cass
    -23.38
    asis
    -23.25
    ros
    -23.25
    Ros
    -23.13
    asses
    -22.88
     Ros
    -22.63
    POSITIVE LOGITS
    まい
    13.88
    荛
    13.06
    dig
    12.81
    nam
    12.75
     Olivier
    12.38
    渑
    12.25
    晖
    12.19
     traf
    12.19
     dial
    12.00
    err
    11.94
    Activations Density 0.118%

    No Known Activations