© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3228
    Prev
    Next
    INDEX
    Explanations

    say person

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     module
    -23.25
    模块
    -23.00
    (module
    -21.88
    	module
    -21.88
    odule
    -20.50
     domain
    -19.75
    /module
    -19.25
    module
    -19.13
    .module
    -18.25
     modules
    -18.25
    POSITIVE LOGITS
     person
    60.50
    person
    54.50
     Person
    53.00
    Person
    51.50
    _person
    49.25
    (person
    41.75
    	person
    40.75
     persons
    40.25
    -person
    40.25
    .person
    38.75
    Activations Density 0.207%

    No Known Activations