© 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. 15528
    Prev
    Next
    INDEX
    Explanations

    say E

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

    No Comments

    Negative Logits
    燠
    -15.94
     Huff
    -15.44
    媾
    -15.25
    rtle
    -14.81
    DOMNode
    -14.56
     Sullivan
    -14.38
    晒
    -14.25
    usra
    -14.13
    qtt
    -13.75
    qx
    -13.63
    POSITIVE LOGITS
     EI
    38.50
    埃
    37.75
    EI
    36.50
     EC
    35.50
     EL
    35.25
    EE
    35.25
    エ
    35.25
     EO
    35.25
    EO
    35.00
     EW
    35.00
    Activations Density 7.291%

    No Known Activations