© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15723
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     Tr
    -23.88
    Tr
    -22.50
    acement
    -21.75
     tr
    -21.50
    -Tr
    -21.13
    acin
    -20.38
     Pl
    -20.25
     Estates
    -19.75
    _pl
    -19.50
    Pl
    -19.38
    POSITIVE LOGITS
    笑脸
    15.31
    晴
    15.25
    崂
    14.69
     closets
    14.56
    箭
    14.31
    二线城市
    14.25
    女神
    14.00
    .Cloud
    13.56
    射手
    13.56
    ian
    13.38
    Activations Density 0.382%

    No Known Activations