© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16284
    Prev
    Next
    INDEX
    Explanations

    say "attention"

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

    No Comments

    Negative Logits
    _del
    -17.00
    Del
    -16.88
    lict
    -16.25
     dep
    -15.56
    .del
    -15.38
    Dep
    -15.25
    del
    -15.19
    depart
    -15.19
    	del
    -15.13
    读
    -15.06
    POSITIVE LOGITS
     attention
    31.38
    attention
    29.75
     Attention
    28.13
    _ATT
    25.63
    _attention
    25.50
     attent
    25.13
    Attention
    24.75
    .att
    24.00
    的关注
    23.25
    关注度
    22.88
    Activations Density 0.136%

    No Known Activations