© 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. 14665
    Prev
    Next
    INDEX
    Explanations

    [code] => [code]

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

    No Comments

    Negative Logits
    Ga
    -22.13
     Ga
    -22.00
     Gates
    -20.25
     Garrett
    -20.25
     gastric
    -19.88
     gad
    -19.88
     Gall
    -18.88
    痧
    -18.88
    硖
    -18.13
    irts
    -17.50
    POSITIVE LOGITS
    篷
    19.13
    ポ
    18.50
    汶
    17.88
    poser
    17.88
    蛹
    16.88
    pollo
    16.75
     Lens
    16.50
     Pey
    16.50
    -horizontal
    16.50
     Jon
    16.50
    Activations Density 0.048%

    No Known Activations