© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14153
    Prev
    Next
    INDEX
    Explanations

    say "mountain"

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

    No Comments

    Negative Logits
    影院
    -16.88
    _vect
    -16.50
    店内
    -16.13
     Macy
    -16.00
     RectTransform
    -16.00
    娼
    -15.69
     thẩm
    -15.50
    公立医院
    -15.44
    之夜
    -15.44
    Products
    -15.44
    POSITIVE LOGITS
     mountain
    34.25
     mountains
    34.00
    峰
    33.00
    山顶
    32.75
    山
    32.50
    Mount
    32.25
     Mount
    31.88
    mount
    31.75
     mount
    31.00
     Mountain
    31.00
    Activations Density 0.505%

    No Known Activations