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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15507
    Prev
    Next
    INDEX
    Explanations

    say inequality

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

    No Comments

    Negative Logits
     strength
    -21.38
    rength
    -18.38
    bundles
    -17.75
     Strength
    -17.63
    strength
    -17.50
    _strength
    -17.38
     swamp
    -16.75
    bundle
    -16.63
    Strength
    -16.50
     Schw
    -15.94
    POSITIVE LOGITS
    控制器
    17.88
    补偿
    17.88
    控制
    17.75
     控
    17.63
    metro
    17.00
    忒
    16.38
    UserController
    16.25
    设计
    16.00
    的设计
    15.69
     controller
    15.50
    Activations Density 0.234%

    No Known Activations