© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3268
    Prev
    Next
    INDEX
    Explanations

    control

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (Controller
    -16.38
     persons
    -16.25
     layers
    -15.69
    oard
    -15.44
     Controller
    -15.13
    controller
    -15.06
    _CONTROLLER
    -15.06
    经纪人
    -15.00
     manager
    -15.00
     amounts
    -14.94
    POSITIVE LOGITS
     control
    34.25
    control
    33.50
    _control
    32.75
    	control
    31.75
    Control
    30.88
     Control
    29.38
    (control
    29.38
    控制
    28.88
    -control
    28.63
    .control
    27.38
    Activations Density 0.014%

    No Known Activations