© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15769
    Prev
    Next
    INDEX
    Explanations

    say colors

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

    No Comments

    Negative Logits
    conds
    -18.75
    ighet
    -16.88
    招股
    -16.63
    tors
    -16.50
     lodging
    -16.38
     Fet
    -16.13
    ultipartFile
    -15.94
    .EventHandler
    -15.94
    蹙
    -15.88
     Parcel
    -15.75
    POSITIVE LOGITS
     blue
    32.75
    蓝
    32.50
    蓝色
    31.13
    绿
    30.13
    blue
    29.38
    藍
    29.38
    BLUE
    29.25
     BLUE
    29.13
     Blue
    29.13
    绿水
    28.00
    Activations Density 0.120%

    No Known Activations