© 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. 2000
    Prev
    Next
    INDEX
    Explanations

    say graph

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

    No Comments

    Negative Logits
    肌肉
    -62.75
    Mus
    -61.75
     muscle
    -58.50
    mus
    -58.25
     Muscle
    -56.50
     muscles
    -53.50
     Mus
    -53.25
     µ
    -51.75
    µ
    -50.75
     mus
    -50.25
    POSITIVE LOGITS
    graph
    20.38
     graph
    20.00
     Graph
    19.75
    Graph
    19.50
    graphs
    19.00
    	graph
    17.88
    _graph
    17.88
     Graphic
    17.13
    inge
    17.00
     GRAPH
    16.50
    Activations Density 0.131%

    No Known Activations