© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13961
    Prev
    Next
    INDEX
    Explanations

    say control

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

    No Comments

    Negative Logits
    (fill
    -14.88
    Extension
    -14.50
    жи
    -14.44
    _extension
    -14.38
     Huff
    -14.13
    /extensions
    -14.13
    .Encode
    -14.06
    gars
    -13.88
     scorer
    -13.69
    Decode
    -13.63
    POSITIVE LOGITS
    控制
    89.50
     control
    88.50
     Control
    81.50
    control
    79.00
     controls
    78.00
    Control
    76.00
     控
    76.00
    -control
    73.50
    _control
    72.00
    	control
    72.00
    Activations Density 1.762%

    No Known Activations