© 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. 1598
    Prev
    Next
    INDEX
    Explanations

    [O] => [O]

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

    No Comments

    Negative Logits
    氧
    -40.00
     oxygen
    -38.00
    氧气
    -37.75
     Oxygen
    -36.25
     Olympic
    -32.50
     OC
    -30.63
     Olympics
    -30.13
    O
    -29.88
     O
    -29.38
    OC
    -29.25
    POSITIVE LOGITS
    药物
    15.19
     drug
    14.31
     Digit
    14.00
    建筑
    13.25
    nds
    13.06
    digits
    12.94
     political
    12.69
     building
    12.69
    drug
    12.44
    政治
    12.44
    Activations Density 0.560%

    No Known Activations