© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14832
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    AdapterFactory
    -17.50
    aminer
    -17.50
     PHI
    -17.25
    ATTER
    -16.75
    ATAB
    -16.75
    CELER
    -16.63
    zers
    -16.38
    zig
    -16.25
    pager
    -16.13
    ACTER
    -15.81
    POSITIVE LOGITS
     quantity
    15.88
    esub
    15.19
    ea
    15.00
    ed
    14.88
    esco
    14.13
    esc
    13.81
    duit
    13.38
    门
    13.19
    erus
    13.00
     écrit
    12.88
    Activations Density 0.033%

    No Known Activations