© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    strain

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

    No Comments

    Negative Logits
    (ver
    -27.75
     VER
    -26.00
    -ver
    -25.75
    ver
    -25.38
    .ver
    -25.13
    _ver
    -25.13
     ver
    -25.00
     Ver
    -24.00
    Ver
    -23.00
    VER
    -22.88
    POSITIVE LOGITS
     strain
    45.25
     strains
    36.75
    strain
    34.00
     strained
    21.50
     Phen
    20.75
     Rad
    19.75
     phen
    19.38
     genome
    18.38
     genotype
    18.25
    苯
    18.25
    Activations Density 0.047%

    No Known Activations