© 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. 1658
    Prev
    Next
    INDEX
    Explanations

    say "ve" words

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

    No Comments

    Negative Logits
    ``↵
    -16.38
    mtree
    -15.69
    tree
    -15.63
     tree
    -15.38
    Trees
    -14.88
     CALLBACK
    -14.75
    �
    -14.75
    低头
    -14.69
    论文
    -14.56
     бумаг
    -14.56
    POSITIVE LOGITS
     ve
    24.13
    _ve
    15.31
     legal
    14.81
     veg
    14.75
    Ve
    14.69
    vided
    14.63
    ve
    14.50
    水域
    13.69
     vegetable
    13.63
     vb
    13.50
    Activations Density 0.033%

    No Known Activations