© 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. 16073
    Prev
    Next
    INDEX
    Explanations

    say "direction"

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

    No Comments

    Negative Logits
    autoload
    -18.50
    搭档
    -18.25
    滁
    -18.00
     cracked
    -17.75
    _cutoff
    -17.13
     cuffs
    -17.00
     Hutch
    -17.00
    utoff
    -16.75
     cages
    -16.63
    促销
    -16.50
    POSITIVE LOGITS
     Direction
    27.25
     direction
    26.88
     Directions
    26.50
     orient
    26.25
     Orient
    25.50
    方向
    25.00
     directions
    24.50
    的方向
    24.50
    -direction
    24.25
    Direction
    24.00
    Activations Density 0.186%

    No Known Activations