© 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. 1959
    Prev
    Next
    INDEX
    Explanations

    say sock

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

    No Comments

    Negative Logits
     gold
    -56.00
    金
    -52.75
    Gold
    -50.00
    gold
    -49.25
     Gold
    -48.50
    黄金
    -47.25
    _gold
    -46.25
     golden
    -44.25
     GOLD
    -44.00
    .gold
    -41.25
    POSITIVE LOGITS
    socket
    18.38
    Socket
    16.13
    sockets
    15.25
     socket
    15.19
     BC
    14.56
     tokenizer
    14.50
     Socket
    14.38
     Martian
    14.31
    sock
    14.25
    BC
    14.13
    Activations Density 0.146%

    No Known Activations