© 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. 2545
    Prev
    Next
    INDEX
    Explanations

    say "curr"

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

    No Comments

    Negative Logits
     fil
    -22.13
    _fil
    -21.00
    Fil
    -20.75
    serializer
    -20.00
    fil
    -19.88
     Serial
    -19.25
     Pen
    -19.13
     serialized
    -19.00
    丝
    -18.88
     Ser
    -18.63
    POSITIVE LOGITS
     curr
    55.25
    curr
    52.00
    (curr
    50.00
    	curr
    48.25
    [curr
    47.75
    .curr
    46.25
    Curr
    39.50
    _curr
    38.25
    cur
    32.25
     cur
    32.25
    Activations Density 0.023%

    No Known Activations