© 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. 16070
    Prev
    Next
    INDEX
    Explanations

    tiny

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

    No Comments

    Negative Logits
     Kund
    -18.88
    oad
    -17.88
    沅
    -17.38
     Rahman
    -17.00
    液
    -16.88
    液压
    -16.75
    (predict
    -16.38
    fromJson
    -16.00
    bomb
    -15.75
    辕
    -15.63
    POSITIVE LOGITS
    微
    27.50
     micro
    27.00
    Tiny
    26.63
    .micro
    26.50
    最小
    26.13
    小微
    25.50
     Micro
    25.38
    micro
    25.38
    Micro
    25.25
    微量
    25.13
    Activations Density 0.445%

    No Known Activations