© 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. 2572
    Prev
    Next
    INDEX
    Explanations

    say "intervention"

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

    No Comments

    Negative Logits
    记
    -18.25
    .memo
    -17.38
    .dim
    -16.63
    記
    -16.50
    Dims
    -16.38
    pole
    -16.25
    手套
    -16.25
    (register
    -15.69
    第三代
    -15.63
     Derek
    -15.56
    POSITIVE LOGITS
     Int
    54.50
    int
    52.75
    Int
    50.00
    -int
    46.00
     intervention
    45.00
     int
    44.25
     Intervention
    44.25
     interv
    42.25
    干预
    41.25
    _int
    41.00
    Activations Density 0.116%

    No Known Activations