© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16009
    Prev
    Next
    INDEX
    Explanations

    say con

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

    No Comments

    Negative Logits
     Neck
    -18.25
    Yaw
    -17.63
    (rotation
    -17.38
     rot
    -17.38
     collar
    -17.25
    -neck
    -17.25
    apixel
    -17.13
    旋转
    -17.13
    (rot
    -16.88
    GridColumn
    -16.75
    POSITIVE LOGITS
     Conan
    20.50
     conc
    20.50
    conc
    20.25
    upro
    18.63
    _con
    18.50
    Cong
    18.13
    con
    18.00
     cong
    18.00
     exh
    18.00
    Con
    17.75
    Activations Density 1.489%

    No Known Activations