© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    [事故] => [灾难]

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

    No Comments

    Negative Logits
    酸
    -47.25
     Acc
    -45.00
     acid
    -42.75
    Ac
    -42.50
    _ac
    -42.25
     Acid
    -42.25
    acid
    -42.25
    AC
    -40.75
    -ac
    -40.75
     AC
    -40.50
    POSITIVE LOGITS
    ubar
    15.19
    lambda
    15.13
     Portugal
    14.94
     lambda
    14.50
    ocha
    14.44
    umo
    14.13
     Lambda
    14.06
    licht
    14.00
     Sweden
    13.94
    山东
    13.63
    Activations Density 0.135%

    No Known Activations