© 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. 15431
    Prev
    Next
    INDEX
    Explanations

    say water

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

    No Comments

    Negative Logits
    (co
    -20.50
    -co
    -20.38
    _co
    -18.50
     Co
    -18.38
    (br
    -18.13
     Grip
    -18.13
     coating
    -17.88
    合作
    -17.88
     CO
    -17.75
    coef
    -17.50
    POSITIVE LOGITS
    瀑布
    18.75
    SHA
    18.13
     waterfall
    17.75
     ell
    17.63
    sparse
    17.38
     ellipse
    17.38
    spinner
    17.25
     Shelby
    17.00
    Stream
    16.88
    STREAM
    16.88
    Activations Density 0.747%

    No Known Activations