© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15805
    Prev
    Next
    INDEX
    Explanations

    say "azaar"

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

    No Comments

    Negative Logits
    ös
    -17.50
    Wizard
    -17.25
    现场
    -16.88
    活动现场
    -16.75
     القوم
    -16.00
    óm
    -15.94
    IMATE
    -15.56
    (sum
    -15.44
     mee
    -15.44
    读后
    -15.38
    POSITIVE LOGITS
     Monterey
    22.63
    upro
    21.75
    油气
    21.63
    沙特
    19.88
     coastline
    18.88
     سعود
    18.50
     Coastal
    18.50
     coastal
    18.00
     Californ
    17.88
     telecom
    17.75
    Activations Density 0.759%

    No Known Activations