© 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. 3295
    Prev
    Next
    INDEX
    Explanations

    parent

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     room
    -15.75
    热搜
    -15.38
     pov
    -15.25
    室
    -14.94
     комнат
    -14.44
    ognition
    -13.94
    场
    -13.88
    pv
    -13.69
    lotte
    -13.63
    ansa
    -13.56
    POSITIVE LOGITS
     parent
    76.00
    parent
    71.00
     Parent
    68.50
    Parent
    68.00
    家长
    64.50
    	parent
    63.25
    (parent
    63.00
    .parent
    61.25
    _parent
    61.25
     parents
    60.00
    Activations Density 0.250%

    No Known Activations