© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 46
    Prev
    Next
    INDEX
    Explanations

    [coined] => [by]

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

    No Comments

    Negative Logits
     KE
    -28.75
     LE
    -28.00
     JE
    -26.38
     CE
    -26.38
     SE
    -25.75
     BE
    -25.63
     HE
    -24.38
     PE
    -23.13
     MA
    -23.13
    KE
    -23.13
    POSITIVE LOGITS
    桓
    18.50
    (SYS
    18.13
    .tbl
    17.75
    mdl
    17.63
    岳阳
    17.38
    LS
    16.88
    RS
    16.50
    傅
    16.25
    BS
    15.94
    枣庄
    15.94
    Activations Density 0.533%

    No Known Activations