© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14089
    Prev
    Next
    INDEX
    Explanations

    say parent

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

    No Comments

    Negative Logits
    纪录
    -20.00
    	record
    -19.75
    _Record
    -19.63
    记录
    -19.50
    record
    -19.25
    .record
    -18.75
    Record
    -18.75
     record
    -18.38
    -record
    -17.75
    _record
    -17.38
    POSITIVE LOGITS
     parent
    18.88
    -parent
    18.63
    玩具
    17.75
    家长
    17.75
    玩耍
    17.50
    遊び
    17.38
    父母
    17.25
    (parent
    17.13
    parent
    17.13
    	parent
    16.75
    Activations Density 0.464%

    No Known Activations