© 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. 15357
    Prev
    Next
    INDEX
    Explanations

    website URLs

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

    No Comments

    Negative Logits
    喷涂
    -20.00
    _screen
    -19.00
    屏幕
    -18.50
     SCREEN
    -17.38
    creens
    -17.25
    Screen
    -16.88
    稀土
    -16.88
     screenWidth
    -16.38
    涂层
    -16.38
    _columns
    -16.25
    POSITIVE LOGITS
    www
    17.13
     www
    16.75
    ile
    15.56
    goals
    15.19
    zens
    15.19
    邑
    15.13
    website
    14.50
    pair
    14.44
    goal
    14.25
    cps
    14.19
    Activations Density 0.040%

    No Known Activations