© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    epoch

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

    No Comments

    Negative Logits
    .ser
    -21.13
     ser
    -19.75
    .det
    -17.88
     det
    -17.00
    :min
    -16.88
     determinant
    -16.75
    管
    -16.63
     araç
    -15.88
    顾
    -15.81
    植
    -15.81
    POSITIVE LOGITS
     episode
    27.88
     epoch
    25.75
    Epoch
    24.50
     Episode
    24.50
    Episode
    24.38
     episodes
    23.63
    _episode
    23.38
     Epoch
    23.25
    epoch
    22.75
    时代
    22.25
    Activations Density 0.038%

    No Known Activations