© 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. 14817
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
     ordin
    -20.63
    Курс
    -19.88
    pll
    -19.88
    EventManager
    -19.25
    .newLine
    -18.75
    isman
    -18.75
    リスク
    -18.75
    モデル
    -18.50
     expectation
    -17.88
    lagen
    -17.75
    POSITIVE LOGITS
    年人
    11.75
     population
    10.94
    ๆ
    10.25
    人均
    10.19
    炽
    10.00
    adi
    10.00
    团
    9.75
    年初
    9.63
    每人
    9.50
    民居
    9.50
    Activations Density 0.011%

    No Known Activations