© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 989
    Prev
    Next
    INDEX
    Explanations

    say "cube"

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

    No Comments

    Negative Logits
     radiation
    -21.13
     photons
    -20.63
     photon
    -19.75
    风筝
    -19.50
    照射
    -19.38
    光电
    -19.25
     Radiation
    -18.88
    缁
    -18.75
     irradi
    -18.75
    紫外线
    -18.50
    POSITIVE LOGITS
     BI
    18.25
     Cub
    17.00
     IData
    16.63
     cube
    16.50
    数据
    16.50
     Data
    16.50
    (cube
    16.38
    业务
    16.25
     cubes
    16.13
     mining
    15.94
    Activations Density 0.163%

    No Known Activations