© 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. 2275
    Prev
    Next
    INDEX
    Explanations

    say "attr"

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

    No Comments

    Negative Logits
     SEM
    -19.00
    SEM
    -16.75
     VER
    -16.75
    -leg
    -15.75
    ver
    -15.69
     Perkins
    -15.56
    quant
    -15.50
    	sem
    -15.50
    .resolution
    -15.00
    出轨
    -14.75
    POSITIVE LOGITS
     attr
    51.00
    	attr
    45.00
     Attr
    44.50
    Attr
    43.75
    (attr
    43.75
    attr
    43.25
    .attr
    40.50
    _attr
    39.25
    [attr
    36.50
     attraction
    31.88
    Activations Density 0.051%

    No Known Activations