© 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. 16191
    Prev
    Next
    INDEX
    Explanations

    say support

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

    No Comments

    Negative Logits
    =row
    -16.75
    омер
    -16.63
    Vertical
    -16.25
    斯塔
    -16.25
     Prim
    -16.13
     vertical
    -15.94
    ourmet
    -15.88
     Vertical
    -15.31
    اس
    -15.31
    Prim
    -15.00
    POSITIVE LOGITS
    支撑
    16.75
    阻力
    16.50
    contributors
    16.38
    驱动
    16.00
    驱
    15.69
     contribution
    15.56
    Support
    15.50
    contrib
    15.31
    红旗
    15.19
    拉动
    15.19
    Activations Density 0.273%

    No Known Activations

    This feature has no known activations.