© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 575
    Prev
    Next
    INDEX
    Explanations

    Catholic social teaching

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

    No Comments

    Negative Logits
     Arabia
    -21.75
    Saudi
    -21.38
     Saudi
    -20.63
    聊城
    -20.38
     Riyadh
    -20.38
    伦敦
    -19.13
     Yemen
    -19.00
    java
    -18.50
     java
    -18.25
    /java
    -18.25
    POSITIVE LOGITS
    ICES
    18.88
    磷
    18.88
    沪
    18.00
    .Box
    17.88
    _hr
    17.38
    ILA
    17.25
     phosph
    17.25
    _ipc
    17.00
     IPC
    16.38
     ipc
    16.25
    Activations Density 0.194%

    No Known Activations