© 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. 2926
    Prev
    Next
    INDEX
    Explanations

    say "ization"

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

    No Comments

    Negative Logits
     mir
    -26.13
     Mir
    -23.25
     mirror
    -22.00
    Mir
    -21.25
     arr
    -20.63
    Mirror
    -20.38
    mirror
    -19.63
    opt
    -18.25
    .opt
    -18.25
     pot
    -18.00
    POSITIVE LOGITS
     Optimization
    22.00
     optimization
    21.25
    (Vec
    19.13
    量化
    18.25
     Serialization
    18.00
     Civilization
    17.88
     Serializer
    17.75
     serialization
    17.25
     civilization
    17.13
     Pose
    17.13
    Activations Density 0.117%

    No Known Activations