© 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. 15876
    Prev
    Next
    INDEX
    Explanations

    say uppercase acronyms

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

    No Comments

    Negative Logits
     Pavel
    -24.75
     Weaver
    -23.88
    天河
    -23.50
    晁
    -23.38
     Bowen
    -23.38
    awa
    -23.00
     Zah
    -21.88
     Kov
    -21.75
     Lov
    -21.63
     pov
    -21.13
    POSITIVE LOGITS
    (vc
    31.88
     LTC
    31.38
    (tc
    28.75
     jc
    28.25
    .tc
    28.25
    hci
    27.63
    (gc
    27.25
     DNC
    27.13
    GC
    27.13
    _tc
    26.75
    Activations Density 6.210%

    No Known Activations