© 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. 14906
    Prev
    Next
    INDEX
    Explanations

    [known as] => [“]

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

    No Comments

    Negative Logits
    atories
    -19.75
     Tags
    -19.00
    _tags
    -17.75
    arks
    -17.00
    Tags
    -16.88
     tags
    -16.88
     tag
    -16.88
    tags
    -16.50
    če
    -16.25
    ilit
    -16.13
    POSITIVE LOGITS
     Relatives
    15.38
    人家
    15.06
    商业
    13.88
    RESH
    13.56
     relatives
    13.44
     transferring
    13.38
    rm
    13.00
    副市长
    12.94
    家属
    12.94
     triangular
    12.81
    Activations Density 0.090%

    No Known Activations