© 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. 15367
    Prev
    Next
    INDEX
    Explanations

    say code keywords

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

    No Comments

    Negative Logits
     TY
    -18.38
    犴
    -16.88
     NSK
    -16.63
    类型
    -16.50
    倾斜
    -16.50
    示范
    -16.38
    ResponseType
    -16.38
    DataTask
    -16.00
    ynos
    -15.81
    nı
    -15.75
    POSITIVE LOGITS
    部門
    15.81
    圓
    15.19
    發展
    14.88
    傷
    14.44
    個人
    14.44
     poly
    14.31
    廚
    14.25
    ateur
    13.88
     socialist
    13.75
    環境
    13.63
    Activations Density 0.294%

    No Known Activations