© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14268
    Prev
    Next
    INDEX
    Explanations

    say description

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

    No Comments

    Negative Logits
    结构
    -24.88
     structures
    -24.75
     structure
    -24.63
     Structure
    -22.63
    structure
    -22.63
    Structure
    -22.38
    _structure
    -22.38
    emodel
    -22.13
    _STRUCTURE
    -21.75
    .structure
    -21.25
    POSITIVE LOGITS
    描述
    21.38
     description
    19.88
     descriptive
    19.63
    Descripcion
    19.63
    desc
    19.63
     describe
    19.50
    (desc
    19.25
    Descriptors
    19.13
    	desc
    19.13
     descri
    19.13
    Activations Density 0.826%

    No Known Activations