© 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. 14629
    Prev
    Next
    INDEX
    Explanations

    say "numbers"

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

    No Comments

    Negative Logits
     Snyder
    -20.75
    胭
    -20.13
     sph
    -20.13
    ernet
    -20.00
     Tanner
    -19.88
    _renderer
    -19.75
     spider
    -19.38
    滾
    -19.25
    _rng
    -19.13
    宣讲
    -19.00
    POSITIVE LOGITS
    乔
    21.75
    姥
    18.63
     Quar
    17.13
     Morrison
    16.63
    kea
    16.25
    -bo
    16.13
    喬
    16.00
    丛林
    15.56
    侯
    15.56
    茂
    15.19
    Activations Density 0.177%

    No Known Activations