© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1673
    Prev
    Next
    INDEX
    Explanations

    Brazilian states

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

    No Comments

    Negative Logits
    手术
    -29.25
     Soc
    -28.88
    𝑆
    -28.75
     SAC
    -28.25
     Surgical
    -28.13
     sulfur
    -28.13
    硫
    -27.88
    Sensor
    -27.75
     SV
    -27.63
    -S
    -27.50
    POSITIVE LOGITS
    sup
    17.13
    口中
    14.75
    s
    14.63
    虢
    13.63
     settlement
    12.75
    ETA
    12.25
    .sup
    12.25
    CAT
    12.19
    供
    12.06
    口
    11.94
    Activations Density 0.618%

    No Known Activations