© 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. 14802
    Prev
    Next
    INDEX
    Explanations

    say "Canadian place names"

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

    No Comments

    Negative Logits
    ums
    -15.81
    Exporter
    -15.81
    -widget
    -15.81
    Painter
    -15.25
    接触
    -14.88
    jer
    -14.81
    ajar
    -14.81
    agrams
    -14.69
    caf
    -14.56
    nement
    -14.50
    POSITIVE LOGITS
    声誉
    17.25
    han
    16.25
     organisations
    14.56
    BED
    14.25
    FindObject
    14.19
    �
    13.81
     organise
    13.75
     authorised
    13.69
    关切
    13.69
    Agency
    13.63
    Activations Density 0.052%

    No Known Activations