© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2361
    Prev
    Next
    INDEX
    Explanations

    say "ctrl"

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

    No Comments

    Negative Logits
    dem
    -19.25
     Dem
    -17.13
    Fac
    -17.00
    ych
    -16.88
    Segment
    -16.25
    树脂
    -16.25
     maxim
    -16.25
    (segment
    -16.25
    resolved
    -16.13
    .fac
    -16.13
    POSITIVE LOGITS
     ctrl
    45.25
    (ctrl
    42.50
     Ctrl
    39.75
    ctrl
    38.50
    控
    38.25
    	ctrl
    36.25
    Ctrl
    36.25
    .ctrl
    36.00
    _ctrl
    35.50
    _CTRL
    30.63
    Activations Density 0.065%

    No Known Activations