© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1119
    Prev
    Next
    INDEX
    Explanations

    [言] => [万]

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

    No Comments

    Negative Logits
    CSS
    -22.88
     CSS
    -19.38
    Fish
    -18.88
    _CSS
    -17.63
    λ
    -17.50
    (css
    -16.88
     Fish
    -16.63
     fish
    -16.63
    Css
    -16.50
     λ
    -16.00
    POSITIVE LOGITS
    科学
    21.13
    streams
    20.00
     science
    19.75
    science
    19.63
    科學
    19.50
    Scient
    18.88
     científ
    18.75
     Scientific
    18.25
     trade
    18.25
     científico
    17.75
    Activations Density 0.430%

    No Known Activations