© 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. 2908
    Prev
    Next
    INDEX
    Explanations

    say "HTML comment"

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

    No Comments

    Negative Logits
    范
    -24.13
     Sam
    -19.50
    .Val
    -19.00
     mut
    -19.00
     val
    -18.50
    义
    -18.13
     sim
    -17.63
    mut
    -17.50
     param
    -17.38
    simulation
    -17.38
    POSITIVE LOGITS
    <!--
    29.00
     <!--
    22.88
     Strategy
    22.25
    	Serial
    21.88
     strategy
    21.50
    (serial
    21.13
    Strategy
    20.88
    Serial
    20.13
    串
    19.88
     serialized
    19.38
    Activations Density 0.031%

    No Known Activations