© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15946
    Prev
    Next
    INDEX
    Explanations

    biology research

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

    No Comments

    Negative Logits
     princess
    -15.88
    werk
    -14.88
    ajs
    -14.56
     jazz
    -14.50
     Ninja
    -14.50
    禅
    -14.38
    公主
    -14.38
    我妈
    -14.13
    vx
    -14.06
    娘
    -14.06
    POSITIVE LOGITS
    arde
    18.00
    ardin
    17.75
    ombine
    17.63
    quí
    16.88
    ósito
    16.38
    obs
    16.38
    ôt
    16.13
    [table
    16.00
    inqu
    16.00
    ards
    16.00
    Activations Density 1.394%

    No Known Activations