© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    bias

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

    No Comments

    Negative Logits
     Biological
    -37.00
    BC
    -35.25
     BC
    -33.75
    生物
    -33.75
    Bi
    -33.75
     biological
    -32.75
     BI
    -32.75
     Bi
    -32.75
    _BC
    -32.50
    BI
    -31.63
    POSITIVE LOGITS
    <b
    12.81
    eneg
    12.75
     Hayden
    12.50
    b
    12.38
     Flake
    12.25
    olina
    12.25
     balance
    12.25
    掖
    12.00
    啬
    11.94
    平衡
    11.81
    Activations Density 1.178%

    No Known Activations