© 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. 3081
    Prev
    Next
    INDEX
    Explanations

    say div

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

    No Comments

    Negative Logits
    位置
    -21.50
     Region
    -21.38
     Enumeration
    -19.50
    角度
    -19.50
     Expression
    -19.13
     Angle
    -18.88
    区内
    -18.63
     Area
    -18.38
     Type
    -18.25
     Entry
    -17.63
    POSITIVE LOGITS
    event
    19.00
     event
    18.50
     events
    17.88
    事件
    17.25
    (events
    17.25
    :event
    16.00
    	event
    16.00
    (event
    15.94
    Luck
    15.88
    履行
    15.88
    Activations Density 0.084%

    No Known Activations