© 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. 16007
    Prev
    Next
    INDEX
    Explanations

    say "weed"

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

    No Comments

    Negative Logits
    -b
    -43.75
    -B
    -42.25
    BI
    -39.75
     BM
    -39.75
    Б
    -38.75
    BS
    -38.75
    BM
    -38.25
    _b
    -38.00
     Б
    -37.50
    BF
    -37.25
    POSITIVE LOGITS
    潲
    15.31
    馘
    13.25
    mnop
    12.69
    仫
    12.63
    饴
    12.56
    ạt
    12.44
     uf
    12.19
    weed
    12.13
    ALLOC
    12.06
     AssemblyCopyright
    11.88
    Activations Density 3.619%

    No Known Activations