© 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. 1755
    Prev
    Next
    INDEX
    Explanations

    imported identifiers

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

    No Comments

    Negative Logits
    ildo
    -15.31
    duct
    -15.06
    asics
    -15.00
    圩
    -14.81
    ductive
    -14.81
    Pdf
    -14.13
    edImage
    -14.06
    Band
    -13.94
    ender
    -13.56
    art
    -13.50
    POSITIVE LOGITS
    bcd
    16.88
    江山
    16.50
    quia
    15.88
     gala
    15.31
    [hash
    15.00
    荦
    14.94
     UTC
    14.75
    赦
    14.69
     Construct
    14.56
    pts
    14.38
    Activations Density 0.316%

    No Known Activations