© 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. 15980
    Prev
    Next
    INDEX
    Explanations

    electron shells

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

    No Comments

    Negative Logits
    牧场
    -19.88
     mãe
    -17.50
    redi
    -17.25
     maxHeight
    -16.25
    的母亲
    -16.25
     contact
    -16.13
     congress
    -15.81
     Visitor
    -15.56
    assa
    -15.50
    oken
    -15.38
    POSITIVE LOGITS
     shells
    24.88
     shell
    22.50
    -sh
    21.38
     orbit
    21.38
     Sham
    20.75
    Elect
    20.63
     Elect
    20.25
    -shell
    19.88
    elect
    19.63
    shell
    19.38
    Activations Density 0.056%

    No Known Activations