© 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. 2921
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
     Mer
    -28.25
     mer
    -27.63
    mer
    -27.25
    Mer
    -25.88
    ter
    -24.00
     MER
    -23.38
    	mem
    -23.00
     mem
    -22.25
     terminal
    -22.13
    MER
    -22.13
    POSITIVE LOGITS
    (Util
    20.25
    .capture
    18.00
     MUT
    17.13
    _quant
    15.94
     filament
    15.81
     Evans
    15.75
    orest
    15.44
     Mans
    15.25
     quant
    15.25
    arden
    15.13
    Activations Density 0.160%

    No Known Activations