© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14895
    Prev
    Next
    INDEX
    Explanations

    citation authors

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

    No Comments

    Negative Logits
    胡子
    -17.88
    ':
↵
    -16.88
    ":
↵
    -16.88
    咒
    -16.50
    怪物
    -15.88
    石膏
    -15.88
    归
    -15.50
    宣传片
    -15.44
    __':
↵
    -15.44
     Kahn
    -15.31
    POSITIVE LOGITS
     prox
    18.13
     Pro
    15.38
     Gór
    15.25
    -Pro
    15.06
     spp
    14.75
    á
    14.56
    Pro
    14.50
     col
    14.44
    imer
    14.44
     nonzero
    14.25
    Activations Density 0.133%

    No Known Activations