© 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. 1204
    Prev
    Next
    INDEX
    Explanations

    [med] => [meditative]

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

    No Comments

    Negative Logits
     med
    -62.25
     Med
    -56.25
    Med
    -54.75
     MED
    -52.25
    _med
    -50.75
    med
    -50.50
     mediation
    -50.00
    -med
    -49.00
    medi
    -48.75
     medi
    -46.75
    POSITIVE LOGITS
    声音
    14.88
     hairs
    14.19
    BarController
    13.75
    鲈
    13.69
    形象
    13.56
    �
    13.50
    CSS
    13.19
    声
    13.00
     fly
    12.94
    _php
    12.69
    Activations Density 0.111%

    No Known Activations