© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    say relation

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

    No Comments

    Negative Logits
     demos
    -16.38
    炊
    -15.81
    aping
    -15.81
    笔
    -15.56
    rsp
    -14.94
    enic
    -14.94
    evin
    -14.88
    rss
    -14.63
    rab
    -14.50
    宝
    -14.44
    POSITIVE LOGITS
     relation
    76.50
     Relation
    75.50
     relations
    75.50
    Relation
    70.00
     Relations
    70.00
    relation
    67.50
    Relations
    65.50
    relations
    63.75
    _relation
    63.25
     rel
    59.50
    Activations Density 0.197%

    No Known Activations