© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    say Sam

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

    No Comments

    Negative Logits
    (lib
    -20.88
     fort
    -19.88
    	lib
    -19.75
     Fort
    -19.50
     lib
    -18.50
    .lib
    -17.88
    configs
    -17.13
    odi
    -16.88
     Lib
    -16.38
     LIB
    -16.38
    POSITIVE LOGITS
     Sam
    69.00
    Sam
    61.25
    范
    57.25
     sam
    54.75
    sam
    47.50
    实习
    43.50
    .sam
    41.50
     param
    40.50
    (param
    40.00
     SAM
    38.50
    Activations Density 0.110%

    No Known Activations