© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14859
    Prev
    Next
    INDEX
    Explanations

    in

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

    No Comments

    Negative Logits
    ads
    -15.88
    .Split
    -15.56
    �能
    -15.50
    ecom
    -15.19
    apper
    -15.00
    业
    -14.81
    微信
    -14.38
    aan
    -14.19
    .EventHandler
    -13.94
    isko
    -13.94
    POSITIVE LOGITS
    汲
    16.25
    子弟
    15.19
    CORD
    15.13
    Interceptor
    14.81
     monarchy
    14.75
     sentiments
    14.56
     impeachment
    14.50
     Grove
    14.50
    签字
    14.19
     mond
    14.13
    Activations Density 0.171%

    No Known Activations