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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15830
    Prev
    Next
    INDEX
    Explanations

    ending with e

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

    No Comments

    Negative Logits
    枭
    -20.63
     Rubin
    -20.25
    卣
    -19.13
    lington
    -18.88
     Thornton
    -18.63
    扬州
    -18.00
    毓
    -17.63
     Salvador
    -17.25
    暹
    -17.00
    逵
    -16.88
    POSITIVE LOGITS
     SCE
    32.25
    ZE
    32.25
    QE
    32.00
     QE
    31.25
    CEE
    29.63
    OE
    28.75
     Greene
    28.38
    鹿
    28.38
    qe
    28.38
    CE
    28.00
    Activations Density 5.131%

    No Known Activations