© 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. 2717
    Prev
    Next
    INDEX
    Explanations

    say "stride"

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

    No Comments

    Negative Logits
    screens
    -17.88
    erde
    -17.25
    (cert
    -16.75
     rel
    -16.75
    师
    -16.25
    erin
    -16.13
    .rel
    -16.00
    Mer
    -15.94
     mirrors
    -15.75
    creens
    -15.50
    POSITIVE LOGITS
    Stride
    38.25
     stride
    37.00
    stride
    36.00
    _stride
    35.25
    .stride
    30.38
     STR
    24.63
    -str
    24.38
    Stra
    23.50
     strides
    23.38
    .Str
    22.50
    Activations Density 0.012%

    No Known Activations