© 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. 1770
    Prev
    Next
    INDEX
    Explanations

    artillery

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

    No Comments

    Negative Logits
    几何
    -18.63
     Architecture
    -18.00
    architecture
    -17.88
     architecture
    -17.75
    (geometry
    -17.25
     geometry
    -16.50
    -security
    -16.13
    材质
    -16.00
    Architecture
    -15.94
     geological
    -15.88
    POSITIVE LOGITS
    剑
    16.13
    EFI
    16.13
     graphs
    15.69
    申博
    15.56
    anking
    14.81
     McA
    14.63
    晔
    14.63
     Dise
    14.63
     Gamer
    14.63
    chool
    14.56
    Activations Density 0.176%

    No Known Activations