© 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. 2623
    Prev
    Next
    INDEX
    Explanations

    Ana

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

    No Comments

    Negative Logits
    	reg
    -20.88
    reg
    -18.75
     Pert
    -18.25
     REG
    -17.75
    pert
    -17.50
    regon
    -17.50
     Dimension
    -17.38
     Regression
    -17.38
     pert
    -17.25
    Dimension
    -17.25
    POSITIVE LOGITS
     Ana
    43.25
    Ana
    40.75
     ana
    35.25
    安
    30.75
    (annotation
    25.25
     ans
    24.88
    甲
    24.88
    乙
    24.75
    (ans
    24.75
     Anal
    23.75
    Activations Density 0.047%

    No Known Activations