© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14369
    Prev
    Next
    INDEX
    Explanations

    say "proper nouns"

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

    No Comments

    Negative Logits
    願
    -16.88
    ilan
    -15.88
    K
    -15.63
    ilingual
    -15.50
    liga
    -15.13
    不得转载
    -15.00
    etch
    -14.75
    iable
    -14.56
    sig
    -14.50
    ilater
    -14.50
    POSITIVE LOGITS
     Walton
    17.00
     Pikachu
    16.75
    PubMed
    15.69
     pa
    15.63
     Prison
    15.63
     poisoned
    15.19
    中毒
    15.13
    Robin
    15.06
     arrests
    14.94
    牢
    14.94
    Activations Density 0.720%

    No Known Activations