© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14667
    Prev
    Next
    INDEX
    Explanations

    say algorithmic concepts

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

    No Comments

    Negative Logits
    经开
    -13.00
    しかも
    -10.94
    -tone
    -10.88
    公然
    -10.69
     %=
    -10.56
     Spicer
    -10.44
    /send
    -10.38
     realised
    -10.31
    Stencil
    -10.00
     ($.
    -10.00
    POSITIVE LOGITS
    ��索
    19.13
    _algo
    18.75
    编程
    18.50
    决策
    18.25
    PT
    17.88
    系统
    17.63
    算法
    17.63
    �
    17.25
    _PR
    17.13
    öt
    17.13
    Activations Density 0.884%

    No Known Activations