© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1264
    Prev
    Next
    INDEX
    Explanations

    say 病

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

    No Comments

    Negative Logits
    精神
    -55.75
    的精神
    -50.00
    Spirit
    -47.75
     spirit
    -47.00
    spirit
    -46.25
     spiritual
    -43.75
     Spirit
    -43.00
     Spiritual
    -41.00
     spiritually
    -40.75
     spirits
    -39.75
    POSITIVE LOGITS
    南海
    15.94
    JSON
    15.63
    ArrayType
    15.44
    calc
    15.31
    ABC
    15.13
     urban
    14.50
     ABC
    14.38
     JSON
    14.13
    .DataGridView
    13.94
    _calc
    13.63
    Activations Density 0.065%

    No Known Activations