© 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. 16084
    Prev
    Next
    INDEX
    Explanations

    say cells

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

    No Comments

    Negative Logits
     pageInfo
    -18.63
    ABI
    -18.00
     Pepsi
    -18.00
    醛
    -17.88
     Trident
    -17.63
    -uri
    -17.50
    riba
    -17.25
    痕
    -16.63
    封面
    -16.50
    契约
    -16.50
    POSITIVE LOGITS
    cells
    43.75
     cells
    43.25
     cell
    42.50
    cell
    41.75
    细胞
    41.50
    CELL
    39.25
     CELL
    38.75
    (cells
    38.50
    _cell
    38.25
    Cell
    38.00
    Activations Density 0.085%

    No Known Activations