© 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. 2481
    Prev
    Next
    INDEX
    Explanations

    say generation

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

    No Comments

    Negative Logits
     norm
    -18.75
    norm
    -17.63
     memo
    -16.88
     norms
    -16.75
    规范
    -16.13
     Gear
    -16.00
    memo
    -15.31
    访谈
    -15.06
    сы
    -14.88
    .rel
    -14.63
    POSITIVE LOGITS
    产生的
    39.50
    产生
    36.75
     generation
    36.00
    產生
    36.00
    产
    34.25
     Generation
    33.75
     generated
    32.75
    Generation
    32.50
    产生了
    31.88
    generated
    31.75
    Activations Density 0.108%

    No Known Activations