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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16210
    Prev
    Next
    INDEX
    Explanations

    say "Att" words

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

    No Comments

    Negative Logits
    层
    -18.88
    eks
    -17.13
    TRAN
    -17.00
    _TRAN
    -16.75
     ε
    -16.63
    (uuid
    -16.25
     Elsa
    -16.13
     layer
    -16.13
     TRAN
    -16.00
    layer
    -15.94
    POSITIVE LOGITS
    _cal
    17.38
    ocal
    17.38
    _ATT
    17.13
     att
    16.75
    	cal
    16.25
    Att
    16.25
     Att
    16.13
    Calculator
    15.19
    _calc
    15.13
     boils
    15.13
    Activations Density 0.031%

    No Known Activations