© 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. 16092
    Prev
    Next
    INDEX
    Explanations

    say bones

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

    No Comments

    Negative Logits
     Bannon
    -23.75
     Edison
    -23.25
     Marvin
    -23.13
     Mana
    -22.75
     Daly
    -21.63
     Casino
    -21.50
     Burnett
    -21.25
    昱
    -21.00
    Mana
    -20.88
     Sonia
    -20.38
    POSITIVE LOGITS
    蚂蚁
    28.00
    蚁
    22.63
    犀
    22.50
     skulls
    21.25
    沆
    21.00
    Rh
    20.50
     Cumberland
    20.13
     Rhino
    20.13
     skeletons
    20.00
    螃蟹
    20.00
    Activations Density 6.171%

    No Known Activations