© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 14154
    Prev
    Next
    INDEX
    Explanations

    [standard] => [output]

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

    No Comments

    Negative Logits
    loadModel
    -19.00
    模型
    -17.88
    :model
    -16.75
    这张
    -16.63
    _allocator
    -16.50
    职权
    -16.25
    ,model
    -16.13
    モデル
    -16.13
    (models
    -16.13
     model
    -15.88
    POSITIVE LOGITS
    输出
    45.50
     output
    41.75
     Output
    38.00
     输出
    37.50
    Output
    37.00
    output
    36.75
     outputs
    35.50
    .output
    34.75
    _output
    34.25
     OUTPUT
    34.00
    Activations Density 0.455%

    No Known Activations