© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15823
    Prev
    Next
    INDEX
    Explanations

    say states

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

    No Comments

    Negative Logits
    鞅
    -19.00
    春
    -17.75
    恽
    -17.00
    厅
    -16.63
    _DLL
    -16.50
    arty
    -16.50
     Suzuki
    -16.50
     Evel
    -16.50
     dialogRef
    -16.38
    雷锋
    -16.38
    POSITIVE LOGITS
    海岸
    17.63
     thermo
    17.13
     Appalach
    15.81
    (states
    15.75
     stati
    15.38
     states
    15.31
     Boards
    14.88
    states
    14.75
    .states
    14.69
     coast
    14.63
    Activations Density 0.134%

    No Known Activations