© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15521
    Prev
    Next
    INDEX
    Explanations

    say turtles

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

    No Comments

    Negative Logits
    氯
    -27.63
     Chlor
    -26.38
     Clifford
    -26.13
     chlor
    -26.00
    (cl
    -25.25
    _cl
    -24.75
    chlor
    -24.75
     cl
    -24.63
     Claus
    -24.13
     chloride
    -24.13
    POSITIVE LOGITS
    瓯
    24.25
    龟
    23.75
     Jeremiah
    22.50
    信阳
    21.38
     Bren
    21.25
    瓠
    21.13
     Turtle
    20.75
    籽
    20.63
     Apollo
    20.50
     turtles
    20.50
    Activations Density 8.001%

    No Known Activations