© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 636
    Prev
    Next
    INDEX
    Explanations

    say axes

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

    No Comments

    Negative Logits
    烟草
    -19.38
    Crypt
    -19.38
    opoly
    -18.25
    SSIP
    -18.25
    私服
    -18.13
     TT
    -17.38
     fibre
    -17.25
    腭
    -17.13
    摩托
    -17.13
     tobacco
    -17.13
    POSITIVE LOGITS
     axs
    24.00
     Axes
    20.38
    _axes
    20.25
     axes
    19.50
    ax
    19.50
    (ax
    19.13
    画
    19.13
     ax
    18.88
    fig
    18.38
    axe
    18.38
    Activations Density 0.074%

    No Known Activations