© 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. 1941
    Prev
    Next
    INDEX
    Explanations

    damaged

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

    No Comments

    Negative Logits
     carrots
    -17.50
    电脑
    -16.88
     Computers
    -16.88
    保险
    -16.50
     Smile
    -16.13
    皖
    -15.88
     GNU
    -15.44
     симв
    -15.38
    吸烟
    -15.31
    挪威
    -15.25
    POSITIVE LOGITS
     graph
    28.75
    	graph
    25.88
     graphs
    25.63
    诗
    25.63
     GRAPH
    25.25
    graph
    24.88
    詩
    24.50
    Graph
    23.88
     Graph
    23.50
     poet
    22.50
    Activations Density 0.316%

    No Known Activations