© 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. 15973
    Prev
    Next
    INDEX
    Explanations

    [Yale] => [Environment]

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

    No Comments

    Negative Logits
     Spr
    -17.38
    alsa
    -17.13
     Spotify
    -16.88
    SPAN
    -16.88
    _sock
    -16.63
    substr
    -16.63
    .SP
    -16.13
     Ala
    -16.13
     algae
    -16.00
     skb
    -15.88
    POSITIVE LOGITS
     Shaw
    18.13
    CLAIM
    17.75
     Burnett
    17.50
    红星
    17.25
    徘徊
    17.00
    imid
    16.88
    盘点
    16.63
    引力
    16.63
     grat
    16.50
    折叠
    16.25
    Activations Density 0.323%

    No Known Activations