© 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. 14625
    Prev
    Next
    INDEX
    Explanations

    [白] => [白]

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

    No Comments

    Negative Logits
    Di
    -19.63
    anzi
    -19.38
    Jane
    -19.25
    .di
    -19.13
    ダイ
    -18.63
    jni
    -18.50
    anio
    -18.50
    PACE
    -18.38
    di
    -18.25
    -di
    -18.25
    POSITIVE LOGITS
    otropic
    19.13
    ot
    18.75
     Bucket
    18.38
     Hampton
    17.63
    桶
    17.38
    鹄
    17.13
    atto
    17.13
    (bucket
    17.00
    croft
    16.88
     Irving
    16.75
    Activations Density 1.231%

    No Known Activations