© 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. 2376
    Prev
    Next
    INDEX
    Explanations

    实习

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

    No Comments

    Negative Logits
     fort
    -20.00
    .variant
    -17.63
    .pres
    -17.13
     Fort
    -17.13
    (lib
    -17.00
    利亚
    -16.50
    variants
    -16.38
    资本
    -16.25
    Perl
    -16.13
    den
    -15.81
    POSITIVE LOGITS
    实习
    57.75
    实习生
    45.25
     Sam
    43.00
    =obj
    38.00
     param
    37.75
    (obj
    37.25
    Sam
    36.50
    (param
    36.25
    [param
    35.00
     obj
    34.75
    Activations Density 0.046%

    No Known Activations