© 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. 15783
    Prev
    Next
    INDEX
    Explanations

    say complex

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

    No Comments

    Negative Logits
    adol
    -15.25
    ayah
    -14.75
     dụ
    -14.50
     aluminium
    -14.44
    iali
    -14.19
     apl
    -14.13
    藻
    -14.13
    �
    -14.13
    -widgets
    -14.00
    aland
    -13.81
    POSITIVE LOGITS
    复杂
    24.50
    Complex
    23.88
    complex
    23.13
     complex
    23.00
    _complex
    21.63
     complexity
    21.38
    艰难
    20.13
    复杂的
    20.13
     complexities
    20.00
    艰苦
    19.50
    Activations Density 0.262%

    No Known Activations