© 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. 2942
    Prev
    Next
    INDEX
    Explanations

    say digital

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

    No Comments

    Negative Logits
    _nums
    -23.25
     nums
    -22.50
     NUM
    -22.13
     numer
    -21.88
    NUM
    -21.25
     Num
    -20.38
    	num
    -20.00
    Num
    -19.00
    nums
    -18.88
     num
    -18.25
    POSITIVE LOGITS
    digital
    36.00
    Digital
    33.25
     digital
    33.00
    .digital
    30.38
     Digital
    30.13
     digitally
    23.38
    igital
    23.38
    (mock
    21.13
     analog
    20.88
    modal
    19.88
    Activations Density 0.055%

    No Known Activations