© 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. 1088
    Prev
    Next
    INDEX
    Explanations

    say Greek letters

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

    No Comments

    Negative Logits
    神经
    -41.25
     neural
    -39.50
     Neural
    -38.75
     neurological
    -33.50
    神经系统
    -31.25
     Neuro
    -31.00
     neuro
    -30.25
     neuronal
    -27.88
     nerve
    -27.50
     Neuroscience
    -27.38
    POSITIVE LOGITS
    ic
    17.38
     Ik
    15.06
    .lambda
    14.06
    Omega
    13.81
    country
    13.75
     Lamb
    13.69
     Lambda
    13.56
     Ul
    13.44
    Alpha
    13.38
    atem
    13.38
    Activations Density 0.138%

    No Known Activations