© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 42
    Prev
    Next
    INDEX
    Explanations

    say people

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

    No Comments

    Negative Logits
    门
    -19.00
    大门
    -18.75
     Engine
    -18.50
     gate
    -18.00
    公安局
    -17.13
    lib
    -16.88
    Gate
    -16.88
    烟火
    -16.75
     gates
    -16.75
     Library
    -16.75
    POSITIVE LOGITS
    seller
    16.63
     jugador
    16.50
     player
    16.25
     getPlayer
    16.13
     PLAYER
    15.56
     seller
    15.56
    ava
    15.56
    鬻
    15.44
     Dota
    15.44
    (station
    15.25
    Activations Density 0.015%

    No Known Activations