© 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. 842
    Prev
    Next
    INDEX
    Explanations

    say Devanagari letters

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

    No Comments

    Negative Logits
    太原
    -17.38
     Mirage
    -16.25
    湟
    -15.88
     GS
    -15.63
    _mes
    -15.44
     GI
    -15.38
    gi
    -15.19
    <Scalars
    -14.69
    �
    -14.63
     wol
    -14.63
    POSITIVE LOGITS
     CT
    27.25
    CT
    26.63
    (ct
    26.00
    	ct
    24.50
    葡萄牙
    22.63
     Portugal
    22.25
     Castro
    21.88
    江门
    21.75
    _CT
    21.75
    苴
    21.63
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.