© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 805
    Prev
    Next
    INDEX
    Explanations

    say king

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

    No Comments

    Negative Logits
     Fuj
    -18.00
    珞
    -17.50
    TextNode
    -16.75
     Manit
    -16.63
    焱
    -15.75
     Hok
    -15.50
    皖
    -15.50
    Ž
    -15.38
    闽
    -15.31
     Wein
    -15.06
    POSITIVE LOGITS
     King
    46.75
    King
    45.25
     king
    45.00
    国王
    43.75
     KING
    43.00
     kings
    38.00
    king
    36.75
     Kings
    35.75
     kingdom
    35.75
     Kingdom
    35.00
    Activations Density 0.192%

    No Known Activations