© 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. 15643
    Prev
    Next
    INDEX
    Explanations

    [...] => low

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

    No Comments

    Negative Logits
    .DOM
    -17.00
    emics
    -17.00
    sembly
    -15.81
    顶部
    -15.44
    时装
    -14.75
    Soft
    -14.69
    Designer
    -14.63
    ipelines
    -14.44
    _LOGGER
    -14.31
    大小
    -14.25
    POSITIVE LOGITS
    bery
    15.56
    �
    15.19
     proficiency
    15.00
     lev
    15.00
     levels
    14.94
     WordPress
    14.69
    caffe
    14.38
     Level
    14.31
    .Level
    14.19
    电量
    14.13
    Activations Density 0.158%

    No Known Activations