© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    [policy] => [policy]

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

    No Comments

    Negative Logits
    政策
    -66.00
     policy
    -64.00
     Policy
    -63.00
    Policy
    -61.75
     policies
    -60.50
     Policies
    -58.50
    policy
    -57.50
    _policy
    -55.75
    -policy
    -55.00
    .policy
    -51.75
    POSITIVE LOGITS
    大脑
    16.63
    脑
    15.44
    -football
    15.13
    蚊
    14.63
     mathematics
    14.63
    brain
    14.00
    数学
    14.00
     Brain
    14.00
    足球
    13.63
    武
    13.56
    Activations Density 0.154%

    No Known Activations