© 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. 2885
    Prev
    Next
    INDEX
    Explanations

    Patricia

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

    No Comments

    Negative Logits
     commands
    -19.38
     commanded
    -17.75
    Sys
    -17.75
    .sys
    -17.63
     registrar
    -17.50
    cmds
    -17.38
     command
    -17.13
     refl
    -16.75
     sys
    -16.63
     Commands
    -16.63
    POSITIVE LOGITS
     Patricia
    27.25
     Antonio
    18.00
    Serialized
    17.00
    (serial
    16.88
     Sergio
    16.00
    (serializer
    15.88
    专利
    15.56
    Feature
    15.50
     serial
    15.50
     MOR
    15.44
    Activations Density 0.019%

    No Known Activations