© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15294
    Prev
    Next
    INDEX
    Explanations

    military ranks

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

    No Comments

    Negative Logits
    umm
    -14.94
    pts
    -14.88
    ess
    -14.88
     Hö
    -14.81
    outers
    -14.81
    ential
    -14.69
    odes
    -14.69
    ến
    -14.31
    oom
    -14.25
    ส
    -14.25
    POSITIVE LOGITS
    .Gen
    16.13
    .microsoft
    16.13
     PRES
    16.13
     Processor
    15.50
    sic
    15.50
    MIC
    14.81
    Friends
    14.81
     Blair
    14.69
     panties
    14.69
    MASK
    14.56
    Activations Density 0.167%

    No Known Activations