© 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. 2775
    Prev
    Next
    INDEX
    Explanations

    say "img"

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

    No Comments

    Negative Logits
     Cent
    -16.00
     facility
    -14.56
     facilit
    -14.50
    ären
    -14.25
     consensus
    -14.25
     TERMIN
    -14.13
    睚
    -13.81
     PEN
    -13.75
    .googlecode
    -13.75
     Tet
    -13.69
    POSITIVE LOGITS
     img
    73.50
    (img
    71.00
    =img
    69.50
    	img
    68.00
    img
    67.00
    ,img
    63.25
    .img
    61.50
     Img
    59.00
    Img
    58.50
    _img
    58.25
    Activations Density 0.049%

    No Known Activations