© 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. 2001
    Prev
    Next
    INDEX
    Explanations

    [paper] => [scrap]

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

    No Comments

    Negative Logits
    纸
    -54.25
     paper
    -54.00
    paper
    -52.25
    -paper
    -49.75
    Paper
    -49.50
    紙
    -49.25
     Paper
    -49.25
    _paper
    -47.25
     papers
    -46.25
     Papers
    -42.00
    POSITIVE LOGITS
    ucket
    16.38
    槽
    14.88
    isson
    14.88
    消防
    14.69
     ECS
    14.69
     Mage
    14.56
     salt
    14.25
    salt
    14.06
     Salt
    14.06
     Fish
    14.06
    Activations Density 0.126%

    No Known Activations