© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1021
    Prev
    Next
    INDEX
    Explanations

    Caesar

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

    No Comments

    Negative Logits
    晋江
    -20.88
     WF
    -20.63
     GN
    -19.50
     WLAN
    -18.88
    ગ
    -18.50
    张家口
    -18.13
     Tasmania
    -18.00
    DSL
    -17.75
    gaard
    -17.50
     Auckland
    -17.38
    POSITIVE LOGITS
     Caesar
    38.00
    楚
    30.13
     CA
    23.13
    郢
    22.75
    .js
    22.75
     Pompe
    22.63
    CA
    22.50
    Ca
    22.13
    秭
    22.00
     Ca
    21.50
    Activations Density 0.026%

    No Known Activations