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

    Neuronpedia

    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. 577
    Prev
    Next
    INDEX
    Explanations

    say "Harry Potter characters"

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

    No Comments

    Negative Logits
    茂名
    -23.88
    兖
    -23.88
    肇庆
    -23.50
    济宁
    -23.38
    菏泽
    -22.63
     Guang
    -22.13
     Indonesia
    -21.88
    汕
    -21.25
    印尼
    -21.13
    在上海
    -20.63
    POSITIVE LOGITS
     Hermione
    42.75
     Hogwarts
    40.50
     Rowling
    39.50
     Dumbledore
    39.50
     Harry
    39.25
     Voldemort
    38.00
     Draco
    37.75
     Snape
    37.75
    Harry
    36.75
    哈利
    36.75
    Activations Density 0.075%

    No Known Activations