© 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. 3345
    Prev
    Next
    INDEX
    Explanations

    say "**"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     chapter
    -21.00
    章
    -19.50
    的数据
    -17.88
    数据
    -17.63
    文件
    -17.50
    部门
    -17.50
    数据分析
    -17.38
     interface
    -17.25
     Chapter
    -17.13
    次会议
    -17.00
    POSITIVE LOGITS
    target
    18.00
    oku
    17.13
     target
    16.88
    agus
    16.75
    model
    16.50
     strength
    16.38
    NDER
    16.25
    _target
    16.13
    point
    16.00
    **
    15.88
    Activations Density 0.033%

    No Known Activations