© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 993
    Prev
    Next
    INDEX
    Explanations

    say "university names"

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

    No Comments

    Negative Logits
    襄阳
    -24.13
    _SQL
    -21.75
    秦皇
    -21.50
     Sql
    -21.50
    Sql
    -21.38
    是韩国
    -21.25
    秦
    -20.88
    sql
    -20.88
     sql
    -20.63
    ,DB
    -20.50
    POSITIVE LOGITS
    IBM
    24.88
     Cornell
    24.63
    MIT
    23.50
     McCarthy
    23.13
    斯坦
    22.88
     Harvard
    21.25
     Eisenhower
    21.25
    NI
    21.00
     MIT
    21.00
     IBM
    20.63
    Activations Density 0.468%

    No Known Activations