© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 568
    Prev
    Next
    INDEX
    Explanations

    programming code

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

    No Comments

    Negative Logits
     Seoul
    -20.88
     Koreans
    -19.63
    绿茶
    -18.75
     Pyongyang
    -18.63
     Korean
    -18.63
    贷
    -18.50
     Korea
    -18.38
    gaard
    -18.38
     Nissan
    -18.25
     Qin
    -18.25
    POSITIVE LOGITS
    oxy
    15.38
    &nbsp
    15.38
    itious
    14.63
     Crystal
    14.19
     crystal
    13.75
    浴室
    13.75
    Crystal
    13.44
     Pipes
    13.38
    �
    13.25
     tub
    13.13
    Activations Density 0.464%

    No Known Activations