© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3185
    Prev
    Next
    INDEX
    Explanations

    numeric literals

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     time
    -17.00
     File
    -16.88
    =file
    -16.75
     Time
    -16.75
    时间
    -16.38
    文件
    -16.13
    组织
    -16.00
    的时间
    -15.56
    akedown
    -15.50
     person
    -15.19
    POSITIVE LOGITS
     modules
    18.75
     INPUT
    17.63
    modules
    17.63
    input
    17.38
     input
    17.00
    INPUT
    16.38
    .components
    16.00
    (components
    15.63
    Input
    15.38
     module
    15.31
    Activations Density 0.013%

    No Known Activations