© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2480
    Prev
    Next
    INDEX
    Explanations

    say "念"

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

    No Comments

    Negative Logits
    pto
    -15.50
    tery
    -15.50
    mond
    -15.31
    玩家来说
    -15.19
    游戏里的
    -14.88
    udes
    -14.81
    ibName
    -14.69
    .Bundle
    -14.50
     Axis
    -14.50
    驻
    -14.38
    POSITIVE LOGITS
    念
    40.50
     nums
    18.63
    nums
    18.25
    放映
    18.00
    num
    17.50
    	num
    17.25
     sentence
    17.00
    憶
    16.88
     num
    16.75
    议员
    16.63
    Activations Density 0.029%

    No Known Activations