© 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. 16234
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

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

    No Comments

    Negative Logits
    碉
    -19.63
    蝶
    -18.88
    家电
    -18.00
    寨
    -17.38
     BBQ
    -17.38
     Viagra
    -17.00
     ног
    -16.88
     gà
    -16.25
     LZ
    -16.13
     DNC
    -16.00
    POSITIVE LOGITS
     Griffith
    17.88
    град
    17.38
    uros
    17.13
    imentary
    15.94
    umin
    15.81
    升华
    15.75
    iddles
    15.38
    арат
    15.19
    ��
    15.19
    udent
    15.19
    Activations Density 1.409%

    No Known Activations