© 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. 16154
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    鳕
    -18.63
    HASH
    -18.63
    蜂蜜
    -18.38
    氨基酸
    -18.25
    奶油
    -18.13
    .beta
    -18.13
    oil
    -17.88
    鬣
    -17.88
    谍
    -17.75
    argo
    -17.63
    POSITIVE LOGITS
     Boone
    19.13
    忠
    16.88
    /ad
    16.75
     adres
    16.63
     QPushButton
    16.38
     offic
    16.25
     Stephens
    16.00
    生死
    15.63
    .addButton
    15.56
     Dead
    15.44
    Activations Density 1.104%

    No Known Activations