© 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. 14412
    Prev
    Next
    INDEX
    Explanations

    location prepositions

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

    No Comments

    Negative Logits
    艮
    -19.88
    ennes
    -15.94
    enne
    -15.81
    �能
    -15.50
    ersh
    -15.38
    ehen
    -15.19
     Shard
    -14.88
    orp
    -14.56
    idal
    -14.50
    uten
    -14.44
    POSITIVE LOGITS
    班组
    16.88
    Brian
    16.13
     Brian
    15.88
     Vance
    15.75
     Blvd
    15.19
    复印件
    15.06
    spect
    14.88
    国防部
    14.88
     spect
    14.75
    lasses
    14.75
    Activations Density 0.120%

    No Known Activations