© 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. 3029
    Prev
    Next
    INDEX
    Explanations

    say 容

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

    No Comments

    Negative Logits
     generations
    -17.13
    generation
    -17.00
    _CUR
    -17.00
     Generation
    -16.63
     genu
    -15.94
    ench
    -15.75
    _generation
    -15.69
    GenerationStrategy
    -15.44
    Generation
    -15.38
    preset
    -15.31
    POSITIVE LOGITS
    容
    56.25
     cap
    35.25
    Cap
    35.00
     Cap
    33.50
    cap
    33.00
     Capac
    28.13
     caps
    27.63
    .cap
    27.63
     capac
    27.38
    -cap
    27.25
    Activations Density 0.057%

    No Known Activations