© 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. 15422
    Prev
    Next
    INDEX
    Explanations

    say "named entities"

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

    No Comments

    Negative Logits
     erect
    -19.88
    	Con
    -18.00
    爨
    -17.75
    -pl
    -17.63
    _pl
    -17.38
    Pl
    -17.00
    操
    -16.88
    /pl
    -16.63
     Pl
    -16.25
     inflate
    -16.25
    POSITIVE LOGITS
     Sussex
    18.88
    禧
    17.00
    孚
    16.25
     Hastings
    16.00
     Clarkson
    15.75
    党工委
    15.56
    PHA
    15.50
     ISO
    15.50
     borderColor
    15.00
     Kushner
    15.00
    Activations Density 0.809%

    No Known Activations