© 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. 2841
    Prev
    Next
    INDEX
    Explanations

    say "training"

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

    No Comments

    Negative Logits
    -hole
    -18.00
    ACA
    -18.00
     очер
    -17.63
     قطر
    -17.63
     vehicle
    -17.50
     Rot
    -17.50
     Jub
    -17.50
    vehicle
    -17.38
     eclipse
    -17.13
    gpio
    -17.00
    POSITIVE LOGITS
    训练
    24.63
     training
    24.00
    training
    21.25
    Training
    21.00
    TRAIN
    20.00
    神经
    20.00
     Training
    19.88
     neural
    19.38
     trained
    19.13
    train
    19.00
    Activations Density 0.095%

    No Known Activations