© 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. 15827
    Prev
    Next
    INDEX
    Explanations

    say "orientation"

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

    No Comments

    Negative Logits
    腊
    -18.13
    Bre
    -17.63
     Fist
    -17.38
    技能
    -17.25
     Qin
    -16.50
     Bre
    -16.38
    茹
    -16.13
    ipe
    -16.00
     Simpson
    -15.75
     controle
    -15.75
    POSITIVE LOGITS
    locator
    19.00
    定位
    18.00
    Declaration
    17.88
     orient
    17.50
    光照
    17.38
     orientations
    17.25
    orientation
    17.13
     orientation
    17.00
    orient
    16.88
     Orient
    16.75
    Activations Density 0.229%

    No Known Activations