© 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. 16100
    Prev
    Next
    INDEX
    Explanations

    say "density"

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

    No Comments

    Negative Logits
    鳐
    -20.63
    Playback
    -18.25
    alist
    -17.88
    鳟
    -17.50
    .detach
    -17.00
    eso
    -16.63
     GTA
    -16.25
    ustral
    -16.25
    白马
    -16.25
    (att
    -16.13
    POSITIVE LOGITS
    密度
    38.00
     density
    38.00
     dens
    37.25
     compressed
    36.75
     compact
    36.25
    密集
    36.00
     dense
    35.75
     compress
    34.75
    density
    34.00
    压缩
    34.00
    Activations Density 0.264%

    No Known Activations