© 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. 15721
    Prev
    Next
    INDEX
    Explanations

    Neuchâtel

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

    No Comments

    Negative Logits
    ki
    -51.50
    -k
    -50.75
     KR
    -49.00
    KS
    -49.00
    KT
    -49.00
    kb
    -48.75
    kt
    -48.50
    ks
    -48.25
    KM
    -48.00
    ky
    -47.75
    POSITIVE LOGITS
    榄
    14.75
    彩
    14.25
    arcer
    14.25
    iphers
    14.06
    浣
    13.94
    蓁
    13.88
     المص
    13.56
    ﺼ
    13.06
    雇主
    12.94
     spons
    12.88
    Activations Density 4.992%

    No Known Activations