© 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. 15935
    Prev
    Next
    INDEX
    Explanations

    do not say in

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

    No Comments

    Negative Logits
    GIN
    -32.50
    rin
    -31.75
     Gin
    -29.88
     Tin
    -29.38
     rin
    -29.25
    gin
    -29.25
    innen
    -28.75
     BIN
    -28.75
    nin
    -28.75
    LIN
    -28.63
    POSITIVE LOGITS
     Hector
    18.75
    蹋
    18.13
     SAC
    17.75
     AAC
    17.75
     Cassidy
    17.38
    OAD
    17.38
    ugar
    17.38
    埭
    16.75
     Todd
    16.75
    髦
    16.63
    Activations Density 4.555%

    No Known Activations