© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    vegetable names

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

    No Comments

    Negative Logits
    peq
    -18.25
    pac
    -18.00
     tic
    -17.38
    庚
    -17.25
     surg
    -16.50
    rectangle
    -16.50
     Pluto
    -16.38
    SPELL
    -16.25
     tq
    -16.13
     Mercedes
    -15.75
    POSITIVE LOGITS
    材料
    16.25
    /js
    15.13
    经济
    15.00
    林业
    14.56
     woods
    14.56
     science
    14.19
     economics
    14.13
     Economic
    14.13
    -js
    13.75
     economy
    13.69
    Activations Density 0.082%

    No Known Activations