© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14517
    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
    aders
    -20.63
    asure
    -18.88
    leys
    -18.38
    bru
    -18.13
    eed
    -17.88
    aths
    -17.75
    artz
    -17.63
    遊
    -17.63
     Mahm
    -17.50
    ously
    -17.38
    POSITIVE LOGITS
    omb
    13.50
    $results
    12.50
    Ub
    11.50
    芮
    11.31
    REPORT
    11.06
     CDDL
    10.88
    在美国
    10.75
    佑
    10.75
    Sh
    10.44
    INV
    10.44
    Activations Density 0.068%

    No Known Activations