© 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. 15138
    Prev
    Next
    INDEX
    Explanations

    1900s years

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

    No Comments

    Negative Logits
     healed
    -17.75
    xFA
    -15.06
    ayout
    -15.00
    昇
    -14.63
     foil
    -14.63
     flair
    -14.56
    xz
    -14.25
    lays
    -13.88
    -area
    -13.75
    ző
    -13.56
    POSITIVE LOGITS
    报
    18.38
    壮
    16.75
    多
    16.13
    寡
    15.88
    .setState
    15.00
    深夜
    14.75
    竹
    14.75
    夜
    14.38
    重大
    14.19
    睡
    14.13
    Activations Density 0.022%

    No Known Activations