© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    say '('

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    azel
    -17.88
    -Americ
    -17.38
    瓮
    -17.25
    (Mouse
    -17.00
     Britt
    -16.63
    Brit
    -16.50
    啤酒
    -16.25
    Eric
    -16.13
    .MOUSE
    -16.00
    詹姆
    -15.88
    POSITIVE LOGITS
    {{$
    29.00
     Laravel
    28.63
     {{$
    27.25
    {!!
    24.75
     {!!
    23.13
    /{{$
    23.00
     {{--
    22.25
    >{{$
    21.38
    aravel
    20.88
    ">{{$
    20.25
    Activations Density 0.108%

    No Known Activations