© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1102
    Prev
    Next
    INDEX
    Explanations

    charts

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

    No Comments

    Negative Logits
    化学
    -31.13
    Chem
    -30.00
     chemical
    -28.88
     chemistry
    -28.63
    _chart
    -28.63
    China
    -28.13
     chemicals
    -27.88
     Chem
    -27.88
     chem
    -27.38
     chart
    -27.25
    POSITIVE LOGITS
    美的
    17.00
    美军
    16.88
    Mus
    16.88
     geometric
    16.00
    美
    15.94
     Mus
    15.94
    几何
    15.81
    aber
    15.50
    军人
    15.19
     Exercise
    14.69
    Activations Density 0.211%

    No Known Activations