© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1086
    Prev
    Next
    INDEX
    Explanations

    say "innovation"

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

    No Comments

    Negative Logits
     Vikings
    -18.00
    地图
    -17.88
     Viking
    -17.38
    大脑
    -16.88
    美术
    -16.88
     Psychiatry
    -16.63
    Diagram
    -16.63
    德州
    -16.25
    _GUI
    -16.13
    graf
    -15.94
    POSITIVE LOGITS
    创新
    18.75
     innovate
    18.63
     innovation
    18.50
     Mojo
    17.50
     Innovation
    17.00
    創新
    16.50
    毛
    15.75
     innov
    15.38
    bird
    15.31
     poison
    15.25
    Activations Density 0.183%

    No Known Activations