© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16118
    Prev
    Next
    INDEX
    Explanations

    [enc] => [ro]

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

    No Comments

    Negative Logits
    RIA
    -17.38
    isma
    -16.63
    -net
    -15.00
    さま
    -15.00
    GOR
    -14.94
    rale
    -14.88
    net
    -14.75
    ност
    -14.56
     Gratuit
    -14.38
    _CYCLE
    -14.31
    POSITIVE LOGITS
    烛
    20.50
     cock
    17.50
    .writeFile
    17.25
     pend
    17.00
    sock
    16.63
    证券交易
    16.38
     coch
    16.38
     fing
    16.38
    ocks
    16.25
     teaspoon
    16.13
    Activations Density 0.090%

    No Known Activations