© 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. 2701
    Prev
    Next
    INDEX
    Explanations

    say norm

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

    No Comments

    Negative Logits
    乙方
    -20.13
    瘤
    -20.00
    甲方
    -17.63
    eros
    -17.13
    pekt
    -15.69
    uter
    -15.44
     erh
    -15.25
    ћ
    -15.19
    .MON
    -14.31
     ter
    -14.19
    POSITIVE LOGITS
     norm
    71.00
     Norm
    66.50
    Norm
    62.75
    norm
    61.25
     norms
    58.00
    (norm
    57.75
    规范
    51.75
    _norm
    49.75
    .norm
    49.50
     Norman
    42.25
    Activations Density 0.100%

    No Known Activations