© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16340
    Prev
    Next
    INDEX
    Explanations

    say "K" words

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

    No Comments

    Negative Logits
    榄
    -16.00
    arcer
    -15.63
    iphers
    -14.88
    浣
    -14.69
     المص
    -14.56
    蓁
    -14.31
    琲
    -13.88
    彩
    -13.50
     spons
    -13.44
    珠海
    -13.31
    POSITIVE LOGITS
    ki
    51.50
    -k
    51.50
    KS
    49.75
    kb
    49.00
     KR
    48.75
    KT
    48.75
    ks
    48.75
    KM
    48.50
    ky
    48.50
    kt
    48.00
    Activations Density 7.161%

    No Known Activations