© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13960
    Prev
    Next
    INDEX
    Explanations

    say study terms

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

    No Comments

    Negative Logits
    (copy
    -17.13
    拷
    -16.75
    運
    -16.13
     Plato
    -15.94
     Copy
    -15.94
    运输
    -15.94
    Copying
    -15.69
    运算
    -15.63
    切割
    -15.56
    导游
    -15.31
    POSITIVE LOGITS
     study
    22.75
     populations
    20.25
     population
    19.50
     Study
    19.50
    追踪
    19.13
    study
    19.00
     sample
    19.00
    Study
    18.50
     monitoring
    17.88
     Coh
    17.75
    Activations Density 0.379%

    No Known Activations